[{"data":1,"prerenderedAt":4144},["ShallowReactive",2],{"9JJStFeYqd":3,"P72sMQvZBU":831,"aRgAbBgvf4":1128,"1jYyHQS8rm":4141},{"siteConfiguration":4,"navigations":81},{"id":5,"siteName":6,"siteDescription":7,"ieee":8,"dateFormat":9,"createdAt":10,"updatedAt":11,"url_path_id":12,"favicon":13,"header":25,"socialLinks":54,"footer":62,"seoMeta":69,"url_path":63},1,"IJCNN 2025","2025 International Joint Conference on Neural Networks (IJCNN)",true,"DDD","2024-07-11T16:38:46.343Z","2025-05-12T22:36:36.226Z","19",{"id":14,"name":15,"alternativeText":16,"caption":16,"width":17,"height":17,"formats":16,"hash":18,"ext":19,"mime":20,"size":21,"url":22,"previewUrl":16,"provider":23,"provider_metadata":16,"createdAt":24,"updatedAt":24},10,"IJCNN-favicon.png",null,101,"IJCNN_favicon_53c6711042",".png","image/png",7.17,"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/IJCNN_favicon_53c6711042.png","strapi-provider-upload-aws-s3-advanced","2024-07-11T16:48:55.263Z",{"id":5,"headerBackground":26,"siteLogo":27,"buttons":44,"affiliate":16},"base-100",{"id":28,"name":29,"alternativeText":16,"caption":16,"width":30,"height":31,"formats":32,"hash":40,"ext":19,"mime":20,"size":41,"url":42,"previewUrl":16,"provider":23,"provider_metadata":16,"createdAt":43,"updatedAt":43},100,"ijcnn25_simple.png",388,63,{"thumbnail":33},{"ext":19,"url":34,"hash":35,"mime":20,"name":36,"path":16,"size":37,"width":38,"height":39},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/thumbnail_ijcnn25_simple_65691ab1f4.png","thumbnail_ijcnn25_simple_65691ab1f4","thumbnail_ijcnn25_simple.png",10.36,245,40,"ijcnn25_simple_65691ab1f4",3.64,"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/ijcnn25_simple_65691ab1f4.png","2024-10-09T23:11:11.161Z",{"id":45,"variation":46,"button":47},3,"Buttons Left",[48],{"id":45,"label":49,"size":50,"color":51,"style":16,"icon":16,"iconPosition":52,"url":53,"newWindow":8,"downloadable":8,"shape":16},"Register Now","btn-sm","btn-primary","End","https://cvent.me/V9QYn8",[55,58],{"id":5,"url":56,"platform":57},"https://www.linkedin.com/company/international-neural-network-society-inns-/","Linkedin",{"id":59,"url":60,"platform":61},2,"https://x.com/INNSociety","Twitter",{"id":5,"prose":63,"confcatsFooter":8,"affiliatesFooter":64,"styles":65},"",false,{"id":66,"edgeTop":67,"edgeBottom":67,"background":68,"containerWidth":16},7,"None","primary",{"id":5,"eventAttendanceMode":70,"startDate":71,"endDate":72,"eventStatus":73,"previousStartDate":16,"locationName":74,"locationStreetAddress":75,"addressLocality":76,"addressRegion":77,"addressCountry":78,"registrationUrl":16,"postalCode":79,"locationUrl":80,"isEvent":8,"affiliate":16},"OfflineEventAttendanceMode","2025-06-30T05:00:00.000Z","2025-07-05T05:00:00.000Z","EventScheduled","Pontifical Gregorian University","Piazza della Pilotta, 4","Rome","RM","Italy","00187","https://www.unigre.it/en/",{"mainNavigation":82,"footerNavigation":825},[83,148,347,498,520,565,723],{"id":5,"title":84,"menuAttached":8,"order":5,"path":85,"type":86,"uiRouterKey":87,"slug":88,"external":64,"items":89},"About","/about","WRAPPER","about","about-1",[90,110,128],{"id":59,"title":91,"menuAttached":8,"order":5,"path":92,"type":93,"uiRouterKey":94,"slug":95,"external":64,"related":96,"items":109},"Organizing Committee","/about/about/organizing-committee","INTERNAL","organizing-committee","about-about-organizing-committee",{"id":14,"heading":91,"createdAt":97,"updatedAt":98,"publishedAt":99,"url_path_id":100,"__contentType":101,"pathAlias":102,"navigationItemId":59,"createdBy":106,"updatedBy":107,"__templateName":108},"2024-09-03T15:36:52.333Z","2024-12-12T17:32:21.846Z","2024-09-03T15:36:53.638Z","50","api::page.page",{"id":103,"url_path":104,"generated":64,"contenttype":101,"createdAt":105,"updatedAt":105},50,"/about/organizing-committee","2024-09-03T15:36:52.340Z",{},{},"Generic",[],{"id":111,"title":112,"menuAttached":8,"order":59,"path":113,"type":93,"uiRouterKey":114,"slug":115,"external":64,"related":116,"items":127},19,"Topics","/about/topics","topics","about-topics",{"id":117,"heading":112,"createdAt":118,"updatedAt":119,"publishedAt":16,"url_path_id":120,"__contentType":101,"pathAlias":121,"navigationItemId":111,"createdBy":125,"updatedBy":126,"__templateName":108},23,"2024-10-11T22:48:47.150Z","2024-10-16T23:47:27.725Z","75",{"id":122,"url_path":113,"generated":64,"contenttype":101,"createdAt":123,"updatedAt":124},75,"2024-10-11T22:48:47.162Z","2024-10-11T22:51:52.271Z",{},{},[],{"id":129,"title":130,"menuAttached":8,"order":45,"path":131,"type":93,"uiRouterKey":132,"slug":133,"external":64,"related":134,"items":147},33,"Important Dates","/about/important-dates","important-dates-1","about-important-dates",{"id":135,"heading":130,"createdAt":136,"updatedAt":137,"publishedAt":138,"url_path_id":139,"__contentType":101,"pathAlias":140,"navigationItemId":129,"createdBy":145,"updatedBy":146,"__templateName":108},22,"2024-10-08T20:28:18.404Z","2025-03-24T18:42:35.388Z","2024-10-08T20:28:30.928Z","69",{"id":141,"url_path":142,"generated":64,"contenttype":101,"createdAt":143,"updatedAt":144},69,"/authors/important-dates","2024-10-08T20:28:18.421Z","2024-10-08T20:28:30.170Z",{},{},[],{"id":149,"title":150,"menuAttached":8,"order":59,"path":151,"type":86,"uiRouterKey":152,"slug":153,"external":64,"items":154},5,"Authors","/authors","authors","authors-1",[155,175,194,213,233,252,271,289,309,329],{"id":14,"title":156,"menuAttached":8,"order":5,"path":157,"type":93,"uiRouterKey":158,"slug":159,"external":64,"related":160,"items":174},"Author Instructions","/authors/author-instructions","author-instructions","authors-author-instructions",{"id":161,"heading":162,"createdAt":163,"updatedAt":164,"publishedAt":165,"url_path_id":166,"__contentType":101,"pathAlias":167,"navigationItemId":14,"createdBy":172,"updatedBy":173,"__templateName":108},15,"Author Instructions ","2024-10-02T18:41:56.425Z","2025-05-02T10:07:00.372Z","2024-10-02T18:46:47.059Z","62",{"id":168,"url_path":169,"generated":64,"contenttype":101,"createdAt":170,"updatedAt":171},62,"/authors/initial-author-instructions","2024-10-02T18:41:56.476Z","2024-12-20T18:59:00.791Z",{},{},[],{"id":176,"title":177,"menuAttached":8,"order":59,"path":178,"type":93,"uiRouterKey":179,"slug":180,"external":64,"related":181,"items":193},41,"Final Paper Submission Instructions","/authors/final-paper-submission-instructions","final-paper-submission-instructions","authors-final-paper-submission-instructions",{"id":182,"heading":177,"createdAt":183,"updatedAt":184,"publishedAt":185,"url_path_id":186,"__contentType":101,"pathAlias":187,"navigationItemId":176,"createdBy":191,"updatedBy":192,"__templateName":108},39,"2025-03-24T19:58:53.266Z","2025-04-28T15:59:27.382Z","2025-03-24T19:58:59.979Z","721",{"id":188,"url_path":178,"generated":64,"contenttype":101,"createdAt":189,"updatedAt":190},721,"2025-03-24T19:58:53.280Z","2025-03-24T19:59:14.329Z",{},{},[],{"id":195,"title":196,"menuAttached":8,"order":45,"path":197,"type":93,"uiRouterKey":198,"slug":199,"external":64,"related":200,"items":212},48,"Presentation Information","/authors/presentation-information","presentation-information","authors-presentation-information",{"id":201,"heading":196,"createdAt":202,"updatedAt":203,"publishedAt":204,"url_path_id":205,"__contentType":101,"pathAlias":206,"navigationItemId":195,"createdBy":210,"updatedBy":211,"__templateName":108},44,"2025-05-14T22:01:57.031Z","2025-06-29T18:02:38.011Z","2025-05-14T22:02:05.172Z","734",{"id":207,"url_path":197,"generated":64,"contenttype":101,"createdAt":208,"updatedAt":209},734,"2025-05-14T22:01:57.043Z","2025-05-14T22:02:04.365Z",{},{},[],{"id":214,"title":215,"menuAttached":8,"order":216,"path":217,"type":93,"uiRouterKey":218,"slug":219,"external":64,"related":220,"items":232},6,"Call for Papers",4,"/authors/authors/call-for-papers","call-for-papers","authors-authors-call-for-papers",{"id":216,"heading":215,"createdAt":221,"updatedAt":222,"publishedAt":223,"url_path_id":224,"__contentType":101,"pathAlias":225,"navigationItemId":214,"createdBy":230,"updatedBy":231,"__templateName":108},"2024-03-13T14:22:16.957Z","2025-04-25T12:39:58.828Z","2024-08-16T23:18:29.626Z","13",{"id":226,"url_path":227,"generated":64,"contenttype":101,"createdAt":228,"updatedAt":229},13,"/authors/call-for-papers","2024-07-11T15:56:51.863Z","2024-07-11T16:51:07.872Z",{},{},[],{"id":234,"title":235,"menuAttached":8,"order":149,"path":236,"type":93,"uiRouterKey":237,"slug":238,"external":64,"related":239,"items":251},34,"Call for Position Papers","/authors/position-papers","call-for-position-papers","authors-position-papers",{"id":234,"heading":235,"createdAt":240,"updatedAt":241,"publishedAt":242,"url_path_id":243,"__contentType":101,"pathAlias":244,"navigationItemId":234,"createdBy":249,"updatedBy":250,"__templateName":108},"2024-12-13T15:39:51.394Z","2025-01-13T13:41:57.712Z","2024-12-13T15:40:00.169Z","111",{"id":245,"url_path":246,"generated":64,"contenttype":101,"createdAt":247,"updatedAt":248},111,"/authors/call-for-position-papers","2024-12-13T15:39:51.411Z","2024-12-13T15:39:59.035Z",{},{},[],{"id":253,"title":254,"menuAttached":8,"order":214,"path":255,"type":93,"uiRouterKey":256,"slug":257,"external":64,"related":258,"items":270},24,"Special Track Papers and Exhibitions","/authors/special-track-papers-and-exhibitions","special-track-papers-and-exhibitions","authors-special-track-papers-and-exhibitions",{"id":259,"heading":254,"createdAt":260,"updatedAt":261,"publishedAt":262,"url_path_id":263,"__contentType":101,"pathAlias":264,"navigationItemId":253,"createdBy":268,"updatedBy":269,"__templateName":108},26,"2024-11-07T14:25:41.160Z","2025-03-06T01:02:52.002Z","2024-11-07T14:29:08.273Z","78",{"id":265,"url_path":255,"generated":64,"contenttype":101,"createdAt":266,"updatedAt":267},78,"2024-11-07T14:25:41.172Z","2024-11-07T16:38:25.925Z",{},{},[],{"id":272,"title":273,"menuAttached":8,"order":66,"path":274,"type":93,"uiRouterKey":275,"slug":276,"external":64,"related":277,"items":288},20,"Call for J2C Papers","/authors/call-for-j-2-c-papers","call-for-j2-c-papers","authors-call-for-j-2-c-papers",{"id":253,"heading":273,"createdAt":278,"updatedAt":279,"publishedAt":280,"url_path_id":281,"__contentType":101,"pathAlias":282,"navigationItemId":272,"createdBy":286,"updatedBy":287,"__templateName":108},"2024-10-22T15:59:42.715Z","2024-10-24T17:30:52.893Z","2024-10-22T16:01:58.336Z","76",{"id":283,"url_path":274,"generated":64,"contenttype":101,"createdAt":284,"updatedAt":285},76,"2024-10-22T15:59:42.735Z","2024-10-22T16:01:57.366Z",{},{},[],{"id":290,"title":291,"menuAttached":8,"order":292,"path":293,"type":93,"uiRouterKey":294,"slug":295,"external":64,"related":296,"items":308},36,"Competitions",8,"/authors/com","competitions","authors-com",{"id":129,"heading":291,"createdAt":297,"updatedAt":298,"publishedAt":299,"url_path_id":300,"__contentType":101,"pathAlias":301,"navigationItemId":290,"createdBy":306,"updatedBy":307,"__templateName":108},"2024-12-10T18:04:59.455Z","2025-02-03T13:44:16.124Z","2024-12-10T18:05:18.883Z","109",{"id":302,"url_path":303,"generated":64,"contenttype":101,"createdAt":304,"updatedAt":305},109,"/program/competitions","2024-12-10T18:04:59.469Z","2024-12-10T18:05:18.030Z",{},{},[],{"id":310,"title":311,"menuAttached":8,"order":312,"path":313,"type":93,"uiRouterKey":314,"slug":315,"external":64,"related":316,"items":328},37,"Special Sessions",9,"/authors/special-sessions","special-sessions","authors-special-sessions",{"id":317,"heading":311,"createdAt":318,"updatedAt":319,"publishedAt":320,"url_path_id":321,"__contentType":101,"pathAlias":322,"navigationItemId":310,"createdBy":326,"updatedBy":327,"__templateName":108},35,"2024-12-13T23:49:57.621Z","2025-06-23T20:45:36.977Z","2024-12-24T09:07:47.591Z","477",{"id":323,"url_path":313,"generated":64,"contenttype":101,"createdAt":324,"updatedAt":325},477,"2024-12-13T23:49:57.635Z","2024-12-24T09:07:41.978Z",{},{},[],{"id":182,"title":330,"menuAttached":8,"order":14,"path":331,"type":93,"uiRouterKey":332,"slug":333,"external":64,"related":334,"items":346},"Workshops","/authors/workshops","workshops","authors-workshops",{"id":310,"heading":330,"createdAt":335,"updatedAt":336,"publishedAt":337,"url_path_id":338,"__contentType":101,"pathAlias":339,"navigationItemId":182,"createdBy":344,"updatedBy":345,"__templateName":108},"2025-01-21T20:10:05.777Z","2025-06-03T21:29:33.466Z","2025-01-22T21:21:32.088Z","693",{"id":340,"url_path":341,"generated":64,"contenttype":101,"createdAt":342,"updatedAt":343},693,"/program/workshops","2025-01-21T20:10:05.790Z","2025-01-21T20:10:12.841Z",{},{},[],{"id":348,"title":349,"menuAttached":8,"order":45,"path":350,"type":86,"uiRouterKey":351,"slug":352,"external":64,"items":353},28,"Program","/program","program","program-3",[354,371,389,408,426,445,463,480],{"id":103,"title":349,"menuAttached":8,"order":5,"path":355,"type":93,"uiRouterKey":356,"slug":357,"external":64,"related":358,"items":370},"/program/program","program-2","program-program",{"id":359,"heading":349,"createdAt":360,"updatedAt":361,"publishedAt":362,"url_path_id":363,"__contentType":101,"pathAlias":364,"navigationItemId":103,"createdBy":368,"updatedBy":369,"__templateName":108},46,"2025-05-28T17:49:06.808Z","2025-05-28T17:49:22.408Z","2025-05-28T17:49:10.470Z","761",{"id":365,"url_path":355,"generated":64,"contenttype":101,"createdAt":366,"updatedAt":367},761,"2025-05-28T17:49:06.827Z","2025-05-28T17:49:22.424Z",{},{},[],{"id":372,"title":373,"menuAttached":8,"order":59,"path":374,"type":93,"uiRouterKey":375,"slug":376,"external":64,"related":377,"items":388},45,"Program at a Glance","/program/program-at-a-glance","program-at-a-glance-1","program-program-at-a-glance",{"id":176,"heading":373,"createdAt":378,"updatedAt":379,"publishedAt":380,"url_path_id":381,"__contentType":101,"pathAlias":382,"navigationItemId":372,"createdBy":386,"updatedBy":387,"__templateName":108},"2025-05-05T21:52:19.148Z","2025-05-29T23:41:38.788Z","2025-05-05T21:52:21.926Z","729",{"id":383,"url_path":374,"generated":64,"contenttype":101,"createdAt":384,"updatedAt":385},729,"2025-05-05T21:52:19.159Z","2025-05-05T21:52:34.936Z",{},{},[],{"id":390,"title":391,"menuAttached":8,"order":45,"path":392,"type":93,"uiRouterKey":393,"slug":394,"external":64,"related":395,"items":407},29,"Keynotes","/program/keynotes","keynotes","program-keynotes",{"id":396,"heading":391,"createdAt":397,"updatedAt":398,"publishedAt":399,"url_path_id":400,"__contentType":101,"pathAlias":401,"navigationItemId":390,"createdBy":405,"updatedBy":406,"__templateName":108},31,"2024-12-02T15:49:41.091Z","2025-06-13T12:50:42.006Z","2024-12-02T15:49:53.487Z","89",{"id":402,"url_path":392,"generated":64,"contenttype":101,"createdAt":403,"updatedAt":404},89,"2024-12-02T15:49:41.103Z","2024-12-02T15:49:52.517Z",{},{},[],{"id":201,"title":409,"menuAttached":8,"order":216,"path":410,"type":93,"uiRouterKey":411,"slug":412,"external":64,"related":413,"items":425},"CIS/INNS Student and Early Career Mentoring Program","/program/ieee-cis-student-and-early-career-mentoring-program-co-organized-by-inns","cis-inns-student-and-early-career-mentoring-program","program-ieee-cis-student-and-early-career-mentoring-program-co-organized-by-inns",{"id":39,"heading":414,"createdAt":415,"updatedAt":416,"publishedAt":417,"url_path_id":418,"__contentType":101,"pathAlias":419,"navigationItemId":201,"createdBy":423,"updatedBy":424,"__templateName":108},"IEEE CIS Student and Early Career Mentoring Program (Co-organized by INNS)","2025-04-04T18:26:36.011Z","2025-07-01T14:27:36.276Z","2025-04-04T18:26:37.250Z","722",{"id":420,"url_path":410,"generated":64,"contenttype":101,"createdAt":421,"updatedAt":422},722,"2025-04-04T18:26:36.024Z","2025-04-04T18:32:37.703Z",{},{},[],{"id":427,"title":428,"menuAttached":8,"order":149,"path":429,"type":93,"uiRouterKey":430,"slug":431,"external":64,"related":432,"items":444},47,"Conference Dinner","/program/conference-dinner","conference-dinner","program-conference-dinner",{"id":433,"heading":428,"createdAt":434,"updatedAt":435,"publishedAt":436,"url_path_id":437,"__contentType":101,"pathAlias":438,"navigationItemId":427,"createdBy":442,"updatedBy":443,"__templateName":108},43,"2025-05-09T16:01:20.812Z","2025-06-10T12:23:50.415Z","2025-05-09T16:01:24.917Z","732",{"id":439,"url_path":429,"generated":64,"contenttype":101,"createdAt":440,"updatedAt":441},732,"2025-05-09T16:01:20.821Z","2025-05-09T16:05:51.779Z",{},{},[],{"id":446,"title":447,"menuAttached":8,"order":214,"path":448,"type":93,"uiRouterKey":449,"slug":450,"external":64,"related":451,"items":462},49,"Tutorials","/program/tutorials","tutorials","program-tutorials",{"id":372,"heading":447,"createdAt":452,"updatedAt":453,"publishedAt":454,"url_path_id":455,"__contentType":101,"pathAlias":456,"navigationItemId":446,"createdBy":460,"updatedBy":461,"__templateName":108},"2025-05-21T23:48:09.741Z","2025-05-29T16:57:19.229Z","2025-05-22T16:59:44.728Z","760",{"id":457,"url_path":448,"generated":64,"contenttype":101,"createdAt":458,"updatedAt":459},760,"2025-05-21T23:48:09.751Z","2025-05-21T23:48:17.313Z",{},{},[],{"id":464,"title":465,"menuAttached":8,"order":66,"path":466,"type":93,"uiRouterKey":467,"slug":468,"external":64,"related":469,"items":479},52,"Conference Photos","/program/conference-photos","conference-photos","program-conference-photos",{"id":427,"heading":465,"createdAt":470,"updatedAt":471,"publishedAt":472,"url_path_id":473,"__contentType":101,"pathAlias":474,"navigationItemId":464,"createdBy":477,"updatedBy":478,"__templateName":108},"2025-07-02T16:17:31.692Z","2025-07-22T13:08:03.744Z","2025-07-02T16:17:34.449Z","771",{"id":475,"url_path":466,"generated":64,"contenttype":101,"createdAt":476,"updatedAt":476},771,"2025-07-02T16:17:31.699Z",{},{},[],{"id":481,"title":482,"menuAttached":8,"order":292,"path":483,"type":93,"uiRouterKey":484,"slug":485,"external":64,"related":486,"items":497},53,"Awards","/program/awards","awards","program-awards",{"id":195,"heading":482,"createdAt":487,"updatedAt":488,"publishedAt":489,"url_path_id":490,"__contentType":101,"pathAlias":491,"navigationItemId":481,"createdBy":495,"updatedBy":496,"__templateName":108},"2025-07-11T13:17:53.226Z","2025-07-11T13:18:04.365Z","2025-07-11T13:18:04.340Z","772",{"id":492,"url_path":483,"generated":64,"contenttype":101,"createdAt":493,"updatedAt":494},772,"2025-07-11T13:17:53.244Z","2025-07-11T13:18:03.233Z",{},{},[],{"id":499,"title":500,"menuAttached":8,"order":216,"path":501,"type":86,"uiRouterKey":502,"slug":503,"external":64,"items":504},42,"Registration","/registration","registration","registration-2",[505],{"id":433,"title":500,"menuAttached":8,"order":5,"path":506,"type":93,"uiRouterKey":502,"slug":507,"external":64,"related":508,"items":519},"/registration/registration","registration-registration",{"id":149,"heading":500,"createdAt":509,"updatedAt":510,"publishedAt":511,"url_path_id":512,"__contentType":101,"pathAlias":513,"navigationItemId":433,"createdBy":517,"updatedBy":518,"__templateName":108},"2024-03-13T14:22:33.303Z","2025-05-20T15:50:51.048Z","2025-03-24T18:54:06.046Z","14",{"id":514,"url_path":501,"generated":8,"contenttype":101,"createdAt":515,"updatedAt":516},14,"2024-07-11T15:56:51.903Z","2025-05-20T15:50:51.065Z",{},{},[],{"id":521,"title":522,"menuAttached":8,"order":149,"path":523,"type":86,"uiRouterKey":524,"slug":525,"external":64,"items":526},21,"Sponsors & Exhibitors","/sponsors-and-exhibitors","sponsors","sponsors-and-exhibitors-1",[527,546],{"id":135,"title":528,"menuAttached":8,"order":5,"path":529,"type":93,"uiRouterKey":530,"slug":531,"external":64,"related":532,"items":545},"Become a Sponsor","/sponsors-and-exhibitors/become-a-sponsor","become-a-sponsor","sponsors-and-exhibitors-become-a-sponsor",{"id":533,"heading":528,"createdAt":534,"updatedAt":535,"publishedAt":536,"url_path_id":537,"__contentType":101,"pathAlias":538,"navigationItemId":135,"createdBy":543,"updatedBy":544,"__templateName":108},11,"2024-09-11T06:01:15.716Z","2025-06-06T14:22:47.849Z","2024-10-17T15:59:57.166Z","56",{"id":539,"url_path":540,"generated":64,"contenttype":101,"createdAt":541,"updatedAt":542},56,"/sponsor/become-a-sponsor","2024-09-11T07:49:05.962Z","2024-10-17T15:59:56.407Z",{},{},[],{"id":359,"title":547,"menuAttached":8,"order":59,"path":548,"type":93,"uiRouterKey":549,"slug":550,"external":64,"related":551,"items":564},"Sponsors and Exhibitors","/sponsors-and-exhibitors/exhibitors-and-sponsors","sponsors-and-exhibitors","sponsors-and-exhibitors-exhibitors-and-sponsors",{"id":499,"heading":552,"createdAt":553,"updatedAt":554,"publishedAt":555,"url_path_id":556,"__contentType":101,"pathAlias":557,"navigationItemId":359,"createdBy":562,"updatedBy":563,"__templateName":108},"Exhibitors and Sponsors","2025-05-06T20:11:58.429Z","2025-06-09T18:56:46.443Z","2025-05-06T20:12:00.076Z","731",{"id":558,"url_path":559,"generated":64,"contenttype":101,"createdAt":560,"updatedAt":561},731,"/sponsor/exhibitors-and-sponsors","2025-05-06T20:11:58.438Z","2025-05-06T20:12:21.833Z",{},{},[],{"id":45,"title":566,"menuAttached":8,"order":214,"path":567,"type":86,"uiRouterKey":568,"slug":569,"external":64,"items":570},"Travel and Grants","/travel","travel-and-grants","travel-2",[571,588,606,623,640,661,680,699,716],{"id":292,"title":572,"menuAttached":8,"order":5,"path":573,"type":93,"uiRouterKey":574,"slug":575,"external":64,"related":576,"items":587},"Venue","/travel/venue","venue","travel-venue",{"id":226,"heading":572,"createdAt":577,"updatedAt":578,"publishedAt":579,"url_path_id":580,"__contentType":101,"pathAlias":581,"navigationItemId":292,"createdBy":585,"updatedBy":586,"__templateName":108},"2024-09-20T19:29:08.274Z","2024-09-22T20:32:54.329Z","2024-09-22T20:32:54.311Z","59",{"id":582,"url_path":573,"generated":64,"contenttype":101,"createdAt":583,"updatedAt":584},59,"2024-09-20T19:29:08.288Z","2024-09-20T19:37:59.949Z",{},{},[],{"id":66,"title":589,"menuAttached":8,"order":59,"path":590,"type":93,"uiRouterKey":591,"slug":592,"external":64,"related":593,"items":605},"How to Reach Rome","/travel/how-to-reach-rome","how-to-reach-rome","travel-how-to-reach-rome",{"id":594,"heading":589,"createdAt":595,"updatedAt":596,"publishedAt":597,"url_path_id":598,"__contentType":101,"pathAlias":599,"navigationItemId":66,"createdBy":603,"updatedBy":604,"__templateName":108},12,"2024-09-19T22:44:04.677Z","2024-09-22T20:33:08.107Z","2024-09-22T20:33:08.091Z","58",{"id":600,"url_path":590,"generated":64,"contenttype":101,"createdAt":601,"updatedAt":602},58,"2024-09-19T22:44:04.690Z","2024-09-20T18:49:51.760Z",{},{},[],{"id":312,"title":607,"menuAttached":8,"order":45,"path":608,"type":93,"uiRouterKey":609,"slug":610,"external":64,"related":611,"items":622},"Local Transportation","/travel/local-transportation","local-transportation","travel-local-transportation",{"id":514,"heading":607,"createdAt":612,"updatedAt":613,"publishedAt":614,"url_path_id":615,"__contentType":101,"pathAlias":616,"navigationItemId":312,"createdBy":620,"updatedBy":621,"__templateName":108},"2024-09-20T19:55:44.966Z","2025-04-03T21:18:49.922Z","2024-09-22T20:33:18.110Z","60",{"id":617,"url_path":608,"generated":64,"contenttype":101,"createdAt":618,"updatedAt":619},60,"2024-09-20T19:55:44.978Z","2024-09-20T19:56:03.594Z",{},{},[],{"id":216,"title":624,"menuAttached":8,"order":216,"path":625,"type":93,"uiRouterKey":626,"slug":627,"external":64,"related":628,"items":639},"Avoid Hotel Fraud","/travel/travel/avoid-hotel-fraud","avoid-hotel-fraud","travel-travel-avoid-hotel-fraud",{"id":45,"heading":624,"createdAt":629,"updatedAt":630,"publishedAt":631,"url_path_id":632,"__contentType":101,"pathAlias":633,"navigationItemId":216,"createdBy":637,"updatedBy":638,"__templateName":108},"2024-02-03T00:09:23.078Z","2024-09-18T13:15:40.233Z","2024-09-18T13:15:40.219Z","12",{"id":594,"url_path":634,"generated":64,"contenttype":101,"createdAt":635,"updatedAt":636},"/travel/avoid-hotel-fraud","2024-07-11T15:56:51.831Z","2024-09-18T13:15:39.213Z",{},{},[],{"id":641,"title":642,"menuAttached":8,"order":149,"path":643,"type":93,"uiRouterKey":644,"slug":645,"external":64,"related":646,"items":660},25,"Accommodations ","/travel/travel/accommodations","accommodations","travel-travel-accommodations",{"id":647,"heading":648,"createdAt":649,"updatedAt":650,"publishedAt":651,"url_path_id":652,"__contentType":101,"pathAlias":653,"navigationItemId":641,"createdBy":658,"updatedBy":659,"__templateName":108},27,"Accommodations","2024-11-13T20:38:43.216Z","2025-05-15T16:22:52.997Z","2024-11-13T20:39:38.700Z","83",{"id":654,"url_path":655,"generated":64,"contenttype":101,"createdAt":656,"updatedAt":657},83,"/travel/accommodations","2024-11-13T20:38:43.235Z","2024-11-13T20:39:36.784Z",{},{},[],{"id":259,"title":662,"menuAttached":8,"order":214,"path":663,"type":93,"uiRouterKey":664,"slug":665,"external":64,"related":666,"items":679},"Travel Grants Program","/travel/travel-grants-program","travel-grants-program","travel-travel-grants-program",{"id":348,"heading":667,"createdAt":668,"updatedAt":669,"publishedAt":670,"url_path_id":671,"__contentType":101,"pathAlias":672,"navigationItemId":259,"createdBy":677,"updatedBy":678,"__templateName":108}," IJCNN 2025 Travel Grants Program","2024-11-20T15:37:28.423Z","2025-05-15T14:55:28.432Z","2024-11-20T15:38:46.251Z","84",{"id":673,"url_path":674,"generated":64,"contenttype":101,"createdAt":675,"updatedAt":676},84,"/travel-grants-program","2024-11-20T15:37:28.437Z","2024-11-20T15:38:39.079Z",{},{},[],{"id":681,"title":682,"menuAttached":8,"order":66,"path":683,"type":93,"uiRouterKey":684,"slug":685,"external":64,"related":686,"items":698},38,"IEEE CIS Travel Grants","/travel/ieee-cis-travel-grants","ieee-cis-travel-grants","travel-ieee-cis-travel-grants",{"id":290,"heading":682,"createdAt":687,"updatedAt":688,"publishedAt":689,"url_path_id":690,"__contentType":101,"pathAlias":691,"navigationItemId":681,"createdBy":696,"updatedBy":697,"__templateName":108},"2025-01-21T19:16:25.350Z","2025-05-15T14:40:49.135Z","2025-01-21T19:16:26.208Z","603",{"id":692,"url_path":693,"generated":64,"contenttype":101,"createdAt":694,"updatedAt":695},603,"/travel-and-grants/ieee-cis-travel-grants","2025-01-21T19:16:25.362Z","2025-01-21T19:25:22.597Z",{},{},[],{"id":39,"title":700,"menuAttached":8,"order":292,"path":701,"type":93,"uiRouterKey":702,"slug":703,"external":64,"related":704,"items":715},"Tours","/travel/tours","tours","travel-tours",{"id":681,"heading":700,"createdAt":705,"updatedAt":706,"publishedAt":707,"url_path_id":708,"__contentType":101,"pathAlias":709,"navigationItemId":39,"createdBy":713,"updatedBy":714,"__templateName":108},"2025-02-04T22:05:50.472Z","2025-06-13T13:04:41.726Z","2025-02-05T18:07:57.539Z","712",{"id":710,"url_path":701,"generated":64,"contenttype":101,"createdAt":711,"updatedAt":712},712,"2025-02-04T22:05:50.491Z","2025-02-04T22:08:49.957Z",{},{},[],{"id":717,"title":718,"menuAttached":8,"order":312,"path":719,"type":86,"uiRouterKey":720,"slug":721,"external":64,"items":722},51,"Things to Do","/travel/https://www.thepalmbeaches.com/explore-cities/boca-raton","things-to-do","travel-https-www-thepalmbeaches-com-explore-cities-boca-raton",[],{"id":161,"title":724,"menuAttached":8,"order":66,"path":725,"type":86,"uiRouterKey":726,"slug":727,"external":64,"items":728},"Reviewers","/reviewer","reviewers-1","reviewer-2",[729,749,768,787,806],{"id":730,"title":731,"menuAttached":8,"order":5,"path":732,"type":93,"uiRouterKey":733,"slug":734,"external":64,"related":735,"items":748},16,"Become a Reviewer","/reviewer/become-a-reviewer","become-a-reviewer","reviewer-become-a-reviewer",{"id":272,"heading":736,"createdAt":737,"updatedAt":738,"publishedAt":739,"url_path_id":740,"__contentType":101,"pathAlias":741,"navigationItemId":730,"createdBy":746,"updatedBy":747,"__templateName":108},"Become a Reviewer ","2024-10-08T20:17:27.285Z","2024-10-08T21:18:53.810Z","2024-10-08T20:17:41.981Z","67",{"id":742,"url_path":743,"generated":64,"contenttype":101,"createdAt":744,"updatedAt":745},67,"/reviewers/become-a-reviewer","2024-10-08T20:17:27.298Z","2024-10-08T20:17:40.527Z",{},{},[],{"id":750,"title":751,"menuAttached":8,"order":59,"path":752,"type":93,"uiRouterKey":753,"slug":754,"external":64,"related":755,"items":767},17,"Become an Area Chair","/reviewer/become-an-area-chair","become-an-area-chair","reviewer-become-an-area-chair",{"id":521,"heading":751,"createdAt":756,"updatedAt":757,"publishedAt":758,"url_path_id":759,"__contentType":101,"pathAlias":760,"navigationItemId":750,"createdBy":765,"updatedBy":766,"__templateName":108},"2024-10-08T20:19:58.538Z","2024-10-08T20:24:35.332Z","2024-10-08T20:20:09.378Z","68",{"id":761,"url_path":762,"generated":64,"contenttype":101,"createdAt":763,"updatedAt":764},68,"/reviewers/become-an-area-chair","2024-10-08T20:19:58.552Z","2024-10-08T20:20:07.852Z",{},{},[],{"id":117,"title":769,"menuAttached":8,"order":45,"path":770,"type":93,"uiRouterKey":771,"slug":772,"external":64,"related":773,"items":786},"Reviewer Guidelines","/reviewer/ijcnn-2025-reviewer-gudelines","reviewer-guidelines-1","reviewer-ijcnn-2025-reviewer-gudelines",{"id":641,"heading":774,"createdAt":775,"updatedAt":776,"publishedAt":777,"url_path_id":778,"__contentType":101,"pathAlias":779,"navigationItemId":117,"createdBy":784,"updatedBy":785,"__templateName":108},"IJCNN 2025 REVIEWER GUDELINES","2024-10-30T18:39:44.668Z","2024-10-30T18:40:04.512Z","2024-10-30T18:40:04.496Z","77",{"id":780,"url_path":781,"generated":64,"contenttype":101,"createdAt":782,"updatedAt":783},77,"/reviewers/ijcnn-2025-reviewer-gudelines","2024-10-30T18:39:44.682Z","2024-10-30T18:40:03.331Z",{},{},[],{"id":647,"title":788,"menuAttached":8,"order":216,"path":789,"type":93,"uiRouterKey":790,"slug":791,"external":64,"related":792,"items":805},"Instructions for Reviewers","/reviewer/instructions-for-reviewers","instructions-for-reviewers-1","reviewer-instructions-for-reviewers",{"id":793,"heading":788,"createdAt":794,"updatedAt":795,"publishedAt":796,"url_path_id":797,"__contentType":101,"pathAlias":798,"navigationItemId":647,"createdBy":803,"updatedBy":804,"__templateName":108},30,"2024-12-02T14:03:41.262Z","2025-05-29T23:45:46.968Z","2024-12-02T14:04:03.266Z","86",{"id":799,"url_path":800,"generated":64,"contenttype":101,"createdAt":801,"updatedAt":802},86,"/reviewers/instructions-for-reviewers","2024-12-02T14:03:41.284Z","2024-12-02T14:04:02.214Z",{},{},[],{"id":793,"title":807,"menuAttached":8,"order":149,"path":808,"type":93,"uiRouterKey":809,"slug":810,"external":64,"related":811,"items":824},"Instructions for Area Chairs","/reviewer/instructions-for-area-chairs","instructions-for-area-chairs","reviewer-instructions-for-area-chairs",{"id":812,"heading":807,"createdAt":813,"updatedAt":814,"publishedAt":815,"url_path_id":816,"__contentType":101,"pathAlias":817,"navigationItemId":793,"createdBy":822,"updatedBy":823,"__templateName":108},32,"2024-12-06T20:22:28.020Z","2024-12-06T20:22:43.448Z","2024-12-06T20:22:43.434Z","94",{"id":818,"url_path":819,"generated":64,"contenttype":101,"createdAt":820,"updatedAt":821},94,"/reviewers/instructions-for-area-chairs","2024-12-06T20:22:28.035Z","2024-12-06T20:22:42.719Z",{},{},[],{"data":16,"error":826},{"status":827,"name":828,"message":829,"details":830},404,"NotFoundError","Entity not found",{},{"affiliates":832},{"affiliates":833},{"data":834,"meta":1126},[835,863,890,936,981,1015,1058,1096],{"id":5,"name":836,"description":63,"createdAt":837,"updatedAt":838,"publishedAt":839,"url_path_id":840,"logo":841,"website":856,"url_path":862},"IEEE","2024-12-02T17:11:39.650Z","2024-12-02T20:27:32.499Z","2024-12-02T17:11:40.945Z","90",{"id":842,"name":843,"alternativeText":16,"caption":16,"width":844,"height":673,"formats":845,"hash":852,"ext":19,"mime":20,"size":853,"url":854,"previewUrl":16,"provider":23,"provider_metadata":16,"createdAt":855,"updatedAt":855},125,"ieee_logo_blue_OD.png",287,{"thumbnail":846},{"ext":19,"url":847,"hash":848,"mime":20,"name":849,"path":16,"size":850,"width":38,"height":851},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/thumbnail_ieee_logo_blue_OD_3633828dcc.png","thumbnail_ieee_logo_blue_OD_3633828dcc","thumbnail_ieee_logo_blue_OD.png",7.46,72,"ieee_logo_blue_OD_3633828dcc",1.37,"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/ieee_logo_blue_OD_3633828dcc.png","2024-12-02T17:11:26.751Z",{"id":681,"variation":46,"button":857},[858],{"id":499,"label":859,"size":50,"color":51,"style":16,"icon":860,"iconPosition":52,"url":861,"newWindow":8,"downloadable":16,"shape":16},"More Info","ChevronRightIcon","https://www.ieee.org/","-48",{"id":59,"name":864,"description":63,"createdAt":865,"updatedAt":866,"publishedAt":867,"url_path_id":868,"logo":869,"website":885,"url_path":889},"CIS","2024-12-02T17:12:32.576Z","2024-12-02T20:27:39.813Z","2024-12-02T17:12:35.318Z","91",{"id":870,"name":871,"alternativeText":16,"caption":16,"width":872,"height":873,"formats":874,"hash":881,"ext":19,"mime":20,"size":882,"url":883,"previewUrl":16,"provider":23,"provider_metadata":16,"createdAt":884,"updatedAt":884},126,"IEEE CIS logo RGB 150ppi.png",472,174,{"thumbnail":875},{"ext":19,"url":876,"hash":877,"mime":20,"name":878,"path":16,"size":879,"width":38,"height":880},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/thumbnail_IEEE_CIS_logo_RGB_150ppi_36fc6fd5ba.png","thumbnail_IEEE_CIS_logo_RGB_150ppi_36fc6fd5ba","thumbnail_IEEE CIS logo RGB 150ppi.png",15.9,90,"IEEE_CIS_logo_RGB_150ppi_36fc6fd5ba",5.08,"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/IEEE_CIS_logo_RGB_150ppi_36fc6fd5ba.png","2024-12-02T17:12:03.475Z",{"id":182,"variation":46,"button":886},[887],{"id":433,"label":859,"size":50,"color":51,"style":16,"icon":860,"iconPosition":52,"url":888,"newWindow":8,"downloadable":16,"shape":16},"https://cis.ieee.org/","-49",{"id":45,"name":891,"description":63,"createdAt":892,"updatedAt":893,"publishedAt":894,"url_path_id":895,"logo":896,"website":931,"url_path":935},"International Neural Network Society","2024-12-02T20:27:24.313Z","2024-12-02T20:27:25.632Z","2024-12-02T20:27:25.624Z","92",{"id":312,"name":897,"alternativeText":16,"caption":16,"width":898,"height":899,"formats":900,"hash":927,"ext":19,"mime":20,"size":928,"url":929,"previewUrl":16,"provider":23,"provider_metadata":16,"createdAt":930,"updatedAt":930},"inns-logo.png",13158,2449,{"large":901,"small":908,"medium":915,"thumbnail":922},{"ext":19,"url":902,"hash":903,"mime":20,"name":904,"path":16,"size":905,"width":906,"height":907},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/large_inns_logo_7be6978ceb.png","large_inns_logo_7be6978ceb","large_inns-logo.png",62.17,1000,186,{"ext":19,"url":909,"hash":910,"mime":20,"name":911,"path":16,"size":912,"width":913,"height":914},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/small_inns_logo_7be6978ceb.png","small_inns_logo_7be6978ceb","small_inns-logo.png",24.61,500,93,{"ext":19,"url":916,"hash":917,"mime":20,"name":918,"path":16,"size":919,"width":920,"height":921},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/medium_inns_logo_7be6978ceb.png","medium_inns_logo_7be6978ceb","medium_inns-logo.png",42.97,750,140,{"ext":19,"url":923,"hash":924,"mime":20,"name":925,"path":16,"size":926,"width":38,"height":359},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/thumbnail_inns_logo_7be6978ceb.png","thumbnail_inns_logo_7be6978ceb","thumbnail_inns-logo.png",8.98,"inns_logo_7be6978ceb",179.01,"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/inns_logo_7be6978ceb.png","2024-07-11T16:45:18.799Z",{"id":39,"variation":46,"button":932},[933],{"id":201,"label":859,"size":50,"color":51,"style":16,"icon":860,"iconPosition":52,"url":934,"newWindow":8,"downloadable":16,"shape":16},"https://www.inns.org/","-50",{"id":216,"name":937,"description":63,"createdAt":938,"updatedAt":939,"publishedAt":940,"url_path_id":941,"logo":942,"website":976,"url_path":980},"Sapienza Universita Di Roma","2024-12-02T20:28:42.398Z","2024-12-02T20:28:44.012Z","2024-12-02T20:28:44.004Z","93",{"id":943,"name":944,"alternativeText":16,"caption":16,"width":945,"height":946,"formats":947,"hash":972,"ext":19,"mime":20,"size":973,"url":974,"previewUrl":16,"provider":23,"provider_metadata":16,"createdAt":975,"updatedAt":975},105,"logo Sapienza.png",2720,1130,{"large":948,"small":954,"medium":960,"thumbnail":966},{"ext":19,"url":949,"hash":950,"mime":20,"name":951,"path":16,"size":952,"width":906,"height":953},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/large_logo_Sapienza_c46660bb24.png","large_logo_Sapienza_c46660bb24","large_logo Sapienza.png",92.22,415,{"ext":19,"url":955,"hash":956,"mime":20,"name":957,"path":16,"size":958,"width":913,"height":959},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/small_logo_Sapienza_c46660bb24.png","small_logo_Sapienza_c46660bb24","small_logo Sapienza.png",38.05,208,{"ext":19,"url":961,"hash":962,"mime":20,"name":963,"path":16,"size":964,"width":920,"height":965},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/medium_logo_Sapienza_c46660bb24.png","medium_logo_Sapienza_c46660bb24","medium_logo Sapienza.png",63.66,312,{"ext":19,"url":967,"hash":968,"mime":20,"name":969,"path":16,"size":970,"width":38,"height":971},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/thumbnail_logo_Sapienza_c46660bb24.png","thumbnail_logo_Sapienza_c46660bb24","thumbnail_logo Sapienza.png",14.84,102,"logo_Sapienza_c46660bb24",46.2,"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/logo_Sapienza_c46660bb24.png","2024-10-11T23:03:47.454Z",{"id":176,"variation":46,"button":977},[978],{"id":372,"label":859,"size":50,"color":51,"style":16,"icon":860,"iconPosition":52,"url":979,"newWindow":8,"downloadable":16,"shape":16},"https://www.uniroma1.it/en/pagina-strutturale/home","-51",{"id":149,"name":982,"description":983,"createdAt":984,"updatedAt":985,"publishedAt":986,"url_path_id":987,"logo":988,"website":1010,"url_path":1014},"SIREN","\u003Cp style=\"text-align:justify;\">\u003Cspan style=\"background-color:rgb(255,255,255);color:rgb(26,32,38);\">Founded in 1989, SIREN (Società Italiana Reti Neuroniche) is Italy's premier and longest-standing society dedicated to Artificial Neural Networks. Its origins are rooted in the pioneering vision of Prof. Eduardo Caianiello, a key figure who established neural network and cybernetics research in Italy and was instrumental in founding institutions like CNR's Laboratory of Cybernetics, and the Italian Institute of Advanced Scientific Studies (IASS) in Vietri sul Mare, SIREN's historical base. Continuing this legacy, SIREN has hosted the annual Italian Workshop on Neural Networks (WIRN) since its foundation, also promoting scientific dissemination, educational training and advanced research by participating in European research projects. The society is currently led by President Prof. Anna Esposito (University of Campania “Luigi Vanvitelli”)\u003C/span>\u003C/p>","2025-05-06T20:08:30.458Z","2025-05-06T20:08:35.913Z","2025-05-06T20:08:35.907Z","730",{"id":989,"name":990,"alternativeText":16,"caption":16,"width":991,"height":992,"formats":993,"hash":1006,"ext":19,"mime":20,"size":1007,"url":1008,"previewUrl":16,"provider":23,"provider_metadata":16,"createdAt":1009,"updatedAt":1009},176,"siren.png",503,214,{"small":994,"thumbnail":1000},{"ext":19,"url":995,"hash":996,"mime":20,"name":997,"path":16,"size":998,"width":913,"height":999},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/small_siren_af15b50165.png","small_siren_af15b50165","small_siren.png",28.23,213,{"ext":19,"url":1001,"hash":1002,"mime":20,"name":1003,"path":16,"size":1004,"width":38,"height":1005},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/thumbnail_siren_af15b50165.png","thumbnail_siren_af15b50165","thumbnail_siren.png",11.84,104,"siren_af15b50165",6.06,"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/siren_af15b50165.png","2025-05-06T20:01:59.290Z",{"id":195,"variation":46,"button":1011},[1012],{"id":717,"label":859,"size":50,"color":51,"style":16,"icon":860,"iconPosition":52,"url":1013,"newWindow":8,"downloadable":8,"shape":16},"https://www.siren-neural-net.it/","-518",{"id":214,"name":1016,"description":1017,"createdAt":1018,"updatedAt":1019,"publishedAt":1020,"url_path_id":1021,"logo":1022,"website":1052,"url_path":1057},"AUBAY ITALIA SPA","\u003Cp style=\"text-align:justify;\">Aubay is a Innovation Company, leader in Europe in the areas of Management Consulting,\u003Cbr>Information & Communication Technology. The group is listed on the NYSE Euronext market in\u003Cbr>Paris, has 7500 employees in 7 countries and 540,3M€ turnover in 2024. We are key player in the\u003Cbr>main market areas, our value is our customers who we support and guide in the path of change.\u003Cbr>Aubay Group is present in Italy with Aubay Italia S.p.A., a company which offers ICT and\u003Cbr>Management Consulting professional services and solutions through experienced professionals\u003Cbr>with a strong know-how in ICT consulting, System Integration and Business Consulting.\u003Cbr>Our project is inspired by a strong entrepreneur attitude which is the base for a real business\u003Cbr>project.\u003Cbr>Continuous growth, profitability and a solid financial position are the key ingredients that\u003Cbr>guarantee us extraordinary and continuous growth. Our financial position is solid: margins are\u003Cbr>always reinvested in the company and there is no middle or long-term debt.\u003Cbr>In more than 20 years of history we built a sound company which is the base for a promising and\u003Cbr>reliable future, we aim to continue to improve a company model with a strong social role and able\u003Cbr>to generate growth, welfare and employment.\u003C/p>","2025-05-29T20:17:59.083Z","2025-05-30T13:43:36.558Z","2025-05-29T20:18:01.616Z","762",{"id":1023,"name":1024,"alternativeText":16,"caption":16,"width":1025,"height":1026,"formats":1027,"hash":1048,"ext":1029,"mime":1032,"size":1049,"url":1050,"previewUrl":16,"provider":23,"provider_metadata":16,"createdAt":1051,"updatedAt":1051},190,"LOGO_AUBAY.jpg",825,874,{"small":1028,"medium":1035,"thumbnail":1041},{"ext":1029,"url":1030,"hash":1031,"mime":1032,"name":1033,"path":16,"size":1034,"width":872,"height":913},".jpg","https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/small_LOGO_AUBAY_80089f7825.jpg","small_LOGO_AUBAY_80089f7825","image/jpeg","small_LOGO_AUBAY.jpg",21.66,{"ext":1029,"url":1036,"hash":1037,"mime":1032,"name":1038,"path":16,"size":1039,"width":1040,"height":920},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/medium_LOGO_AUBAY_80089f7825.jpg","medium_LOGO_AUBAY_80089f7825","medium_LOGO_AUBAY.jpg",37.56,708,{"ext":1029,"url":1042,"hash":1043,"mime":1032,"name":1044,"path":16,"size":1045,"width":1046,"height":1047},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/thumbnail_LOGO_AUBAY_80089f7825.jpg","thumbnail_LOGO_AUBAY_80089f7825","thumbnail_LOGO_AUBAY.jpg",4.93,147,156,"LOGO_AUBAY_80089f7825",44.93,"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/LOGO_AUBAY_80089f7825.jpg","2025-05-29T20:22:37.101Z",{"id":464,"variation":46,"button":1053},[1054],{"id":1055,"label":859,"size":50,"color":51,"style":16,"icon":860,"iconPosition":52,"url":1056,"newWindow":8,"downloadable":8,"shape":16},55,"https://www.aubay.it/","-545",{"id":66,"name":1059,"description":63,"createdAt":1060,"updatedAt":1061,"publishedAt":1062,"url_path_id":1063,"logo":1064,"website":16,"url_path":1095},"Intesa Sanpaolo","2025-05-30T12:58:23.355Z","2025-05-30T12:58:26.612Z","2025-05-30T12:58:26.605Z","763",{"id":1065,"name":1066,"alternativeText":16,"caption":16,"width":1067,"height":1068,"formats":1069,"hash":1091,"ext":1029,"mime":1032,"size":1092,"url":1093,"previewUrl":16,"provider":23,"provider_metadata":16,"createdAt":1094,"updatedAt":1094},210,"INTESA SANPAOLO_COL.jpg",2103,236,{"large":1070,"small":1076,"medium":1081,"thumbnail":1086},{"ext":1029,"url":1071,"hash":1072,"mime":1032,"name":1073,"path":16,"size":1074,"width":906,"height":1075},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/large_INTESA_SANPAOLO_COL_6a2878bba1.jpg","large_INTESA_SANPAOLO_COL_6a2878bba1","large_INTESA SANPAOLO_COL.jpg",20.8,112,{"ext":1029,"url":1077,"hash":1078,"mime":1032,"name":1079,"path":16,"size":1080,"width":913,"height":539},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/small_INTESA_SANPAOLO_COL_6a2878bba1.jpg","small_INTESA_SANPAOLO_COL_6a2878bba1","small_INTESA SANPAOLO_COL.jpg",8.86,{"ext":1029,"url":1082,"hash":1083,"mime":1032,"name":1084,"path":16,"size":1085,"width":920,"height":673},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/medium_INTESA_SANPAOLO_COL_6a2878bba1.jpg","medium_INTESA_SANPAOLO_COL_6a2878bba1","medium_INTESA SANPAOLO_COL.jpg",15.05,{"ext":1029,"url":1087,"hash":1088,"mime":1032,"name":1089,"path":16,"size":1090,"width":38,"height":348},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/thumbnail_INTESA_SANPAOLO_COL_6a2878bba1.jpg","thumbnail_INTESA_SANPAOLO_COL_6a2878bba1","thumbnail_INTESA SANPAOLO_COL.jpg",3.36,"INTESA_SANPAOLO_COL_6a2878bba1",50.57,"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/INTESA_SANPAOLO_COL_6a2878bba1.jpg","2025-05-30T12:58:19.967Z","-546",{"id":292,"name":1097,"description":1098,"createdAt":1099,"updatedAt":1100,"publishedAt":1101,"url_path_id":1102,"logo":1103,"website":1119,"url_path":1125},"IEEE Power & Energy Society","\u003Cp>\u003Cspan style=\"background-color:rgb(255,255,255);color:rgb(26,32,38);\">The Power & Energy Society (PES) provides the world’s largest forum for sharing the latest in technological developments in the electric power industry, for developing standards that guide the development and construction of equipment and systems, and for educating members of the industry and the general public. Members of the Power & Energy Society are leaders in this field, and they — and their employers — derive substantial benefits from involvement with this unique and outstanding association.\u003C/span>\u003C/p>","2025-06-09T18:55:44.049Z","2025-06-09T18:55:53.457Z","2025-06-09T18:55:53.451Z","768",{"id":1104,"name":1105,"alternativeText":16,"caption":16,"width":1106,"height":1107,"formats":1108,"hash":1115,"ext":1029,"mime":1032,"size":1116,"url":1117,"previewUrl":16,"provider":23,"provider_metadata":16,"createdAt":1118,"updatedAt":1118},215,"PES.jpg",357,248,{"thumbnail":1109},{"ext":1029,"url":1110,"hash":1111,"mime":1032,"name":1112,"path":16,"size":1113,"width":1114,"height":1047},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/thumbnail_PES_3653cd5618.jpg","thumbnail_PES_3653cd5618","thumbnail_PES.jpg",10.08,225,"PES_3653cd5618",21.69,"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/PES_3653cd5618.jpg","2025-06-09T18:54:57.178Z",{"id":1120,"variation":46,"button":1121},54,[1122],{"id":1123,"label":859,"size":50,"color":51,"style":16,"icon":860,"iconPosition":52,"url":1124,"newWindow":8,"downloadable":8,"shape":16},57,"https://ieee-pes.org/","-551",{"pagination":1127},{"page":5,"pageSize":641,"pageCount":5,"total":292},{"id":317,"heading":311,"pageHeader":1129,"sections":1130},{"id":317,"description":16,"showPageHeader":8,"backgroundColor":68,"image":16},[1131],{"id":45,"__component":1132,"componentVariation":1133,"contactsVariation":1134,"styles":16,"header":16,"sessionsGroup":1135},"content.sessions","Sessions Sidebar Navigation Contacts Bottom","Card Contact Full",[1136],{"id":45,"groupTitle":16,"sessions":1137},[1138,1163,1190,1216,1267,1294,1335,1378,1427,1501,1570,1614,1633,1691,1731,1767,1802,1844,1887,1929,1979,2012,2031,2058,2092,2133,2175,2209,2252,2295,2330,2364,2443,2486,2506,2562,2605,2624,2671,2696,2731,2765,2798,2863,2885,2927,2976,3011,3040,3058,3074,3124,3183,3244,3284,3305,3324,3362,3394,3434,3469,3494,3522,3570,3609,3634,3653,3681,3709,3758,3827,3845,3895,3938,3964,4008,4021,4068,4108],{"id":216,"session":1139},{"id":216,"title":1140,"teaser":1141,"body":1142,"createdAt":1143,"updatedAt":1144,"publishedAt":1145,"url_path_id":1146,"contacts":1147,"url_path":1162},"Addressing challenges in Nuclear Fusion with Machine Learning","\u003Cp style=\"text-align:justify;\">The quest for commercial fusion power is gaining momentum thanks to the use of artificial intelligence (AI) in nuclear fusion research. The process of nuclear fusion, which mimics the reaction happening in the sun, has the potential to produce energy that is safe, clean, and nearly infinite. The interest in fusion has risen recently, with companies racing to deliver commercial fusion and increased collaboration with government programs. Despite the promising advances, significant challenges remain. The path to commercial fusion will require massive investments and an expanded workforce of skilled researchers and engineers. International collaboration is also essential to share knowledge and experimental techniques, pushing fusion research closer to practical deployment. \u003C/p>","\u003Cp style=\"text-align:justify;\">Recent scientific discoveries must be translated into reactor designs, materials, and cost-cutting techniques that can be produced economically. In this framework, artificial intelligence (AI) and machine learning (ML) are emerging as ground-breaking technologies that could cut the development time by decades. Machine learning is being applied in numerous areas of fusion research. The applications of Machine Learning in fusion science can be traced back to the use of machine learning for disruption prediction since the 1990s. \u003C/p>\u003Cp style=\"text-align:justify;\">Nowadays, applications of neural networks in the fusion community are increasing rapidly, and examples are plasma tomography, the identification of specific events, object detection and tracking, model identification and real-time control. Data-driven science supports scientists in offline analysis and the real-time control of complex experiments. Moreover, AI accelerates exploring potential fusion reactor design, enabling faster, cost-effective design evaluations. AI’s transformative potential in fusion is already evident, but its full capabilities are only beginning to emerge. From predicting plasma behaviours to accelerating reactor design optimization, AI provides tools to solve the most complex fusion challenges. As fusion research evolves, AI and high-performance computing will be critical to realizing the vision of clean, safe, and sustainable fusion power.  \u003C/p>\u003Cp style=\"text-align:justify;\">This special session entitled “Addressing challenges in Nuclear Fusion with Machine Learning” invites contributions from the AI and fusion research communities to explore the latest AI advancements and applications in fusion energy. Key areas of focus include plasma disruption prediction and off-normal event detection, predictive modelling, plasma diagnostics and control, fusion reactor design, and optimizing materials for fusion reactors. The session, through presentations, case studies and discussions, aims to accelerate fusion progress by fostering collaboration and innovation, enabling the global fusion community to meet the scientific, engineering, and economic challenges on the path to scalable fusion power.\u003C/p>","2024-12-13T23:44:20.742Z","2024-12-13T23:47:39.977Z","2024-12-13T23:47:39.970Z","410",[1148,1156],{"id":1149,"name":1150,"committee":16,"position":16,"affiliation":1151,"email":16,"biography":16,"createdAt":1152,"updatedAt":1152,"url_path_id":1153,"contactPhoto":16,"socialLinks":1154,"url_path":1155},275,"Enrico Aymerich","University of Cagliari","2024-12-13T23:37:34.363Z","326",[],"-122",{"id":1114,"name":1157,"committee":16,"position":16,"affiliation":1151,"email":16,"biography":16,"createdAt":1158,"updatedAt":1158,"url_path_id":1159,"contactPhoto":16,"socialLinks":1160,"url_path":1161},"Alessandra Fanni","2024-12-13T23:37:19.737Z","276",[],"-72","-206",{"id":149,"session":1164},{"id":149,"title":1165,"teaser":1166,"body":1167,"createdAt":1168,"updatedAt":1169,"publishedAt":1170,"url_path_id":1171,"contacts":1172,"url_path":1189},"Advances in Compression Techniques for Scalable and Efficient Deep Neural Networks","\u003Cp style=\"text-align:justify;\">In the era of deep learning, where neural networks are widely deployed across diverse applications, the demand for scalable, efficient models has never been higher. This special session on Neural Network Compression Techniques aims to address the growing challenges of computational overhead, memory constraints, and energy consumption in deploying deep learning models on resource-limited devices and in distributed environments.\u003C/p>","\u003Cp style=\"text-align:justify;\">Traditional deep learning models are often too resource-intensive for realtime applications in fields such as healthcare, IoT, and fog computing, where latency, power efficiency, and reliability are critical. As neural networks continue to expand in complexity and size, innovative compression techniques—such as pruning, quantization, and knowledge distillation—have become essential for maintaining performance while reducing model size and computation costs. The primary objectives of this session are to bring together experts in neural network compression, showcase the latest methodologies that enhance computational efficiency, and foster discussions on multi-objective optimization for balanced trade-offs in accuracy, latency, and resource usage. \u003C/p>\u003Cp style=\"text-align:justify;\">A core focus will be on evolutionary and multi-objective optimization methods that enable highly efficient model deployment without sacrificing quality, particularly in energy-conscious and latency-sensitive applications.\u003C/p>","2024-12-13T23:44:21.392Z","2025-01-13T15:26:36.390Z","2024-12-13T23:52:10.821Z","411",[1173,1181],{"id":1174,"name":1175,"committee":16,"position":16,"affiliation":1176,"email":16,"biography":63,"createdAt":1177,"updatedAt":1177,"url_path_id":1178,"contactPhoto":16,"socialLinks":1179,"url_path":1180},359,"Rahma Fourati","ReGIM-Lab","2024-12-13T23:51:57.752Z","478",[],"-273",{"id":1182,"name":1183,"committee":16,"position":16,"affiliation":1184,"email":16,"biography":63,"createdAt":1185,"updatedAt":1185,"url_path_id":1186,"contactPhoto":16,"socialLinks":1187,"url_path":1188},466,"Jihene Tmamna","ReGIM-Lab, University of Sfax","2025-01-13T15:26:07.889Z","600",[],"-394","-207",{"id":214,"session":1191},{"id":214,"title":1192,"teaser":1193,"body":1194,"createdAt":1195,"updatedAt":1196,"publishedAt":1197,"url_path_id":1198,"contacts":1199,"url_path":1215},"Advances in Deep Learning for Biomedical Data Analysis","\u003Cp style=\"text-align:justify;\">Biomedical data analysis involves the treatment of the physiological electrical activities measured using sensors placed on a living thing, also the medical imaging, allowing it to provide a useful process for abnormality detection and diagnosis purposes. Recently, Deep Learning (DL) has received a great attention to solve difficult and complex problems related to biosignal and medical image processing, where the traditional signal/image processing algorithms and conventional machine learning techniques have shown their limitations to solve such problems. \u003C/p>","\u003Cp style=\"text-align:justify;\">Indeed, the recent advances in this area have brought impressive progress to solve several practical and difficult problems in many fields including medicine, healthcare, e-health, neuroscience, brain-computer interface (BCI), neurofeedback, robotics, robotic exoskeletons, and biometrics, etc. In this context, advanced DL models, have shown their effectiveness to resolve various problems of detection, classification, clustering, prediction, segmentation, diagnosis, etc.; thus, becomes useful solutions to be investigated more for other open problems. The aim of this special session is to bring together researchers and scientists in the fields of biomedical signal and image processing, artificial intelligence and artificial learning, to present and discuss the recent advances in DL algorithms and methods applied for biomedical data processing.\u003C/p>","2024-12-13T23:44:22.037Z","2024-12-13T23:54:16.302Z","2024-12-13T23:54:16.296Z","412",[1200,1208],{"id":1201,"name":1202,"committee":16,"position":16,"affiliation":1203,"email":16,"biography":16,"createdAt":1204,"updatedAt":1204,"url_path_id":1205,"contactPhoto":16,"socialLinks":1206,"url_path":1207},339,"Larbi Boubchir","University of Paris 8","2024-12-13T23:38:00.095Z","390",[],"-186",{"id":1209,"name":1210,"committee":16,"position":16,"affiliation":1203,"email":16,"biography":16,"createdAt":1211,"updatedAt":1211,"url_path_id":1212,"contactPhoto":16,"socialLinks":1213,"url_path":1214},251,"Boubaker Daachi","2024-12-13T23:37:27.040Z","302",[],"-98","-208",{"id":66,"session":1217},{"id":66,"title":1218,"teaser":1219,"body":1220,"createdAt":1221,"updatedAt":1222,"publishedAt":1223,"url_path_id":1224,"contacts":1225,"url_path":1266},"Advances in Time-Series Data: Novel Theories, Methods, and Applications","\u003Cp style=\"text-align:justify;\">The proposed special session, \"Advances in Time-Series Data: Novel Theories, Methods, and Applications,\" aims to address the rapidly growing research area of time-series data analysis, which has profound implications across a wide array of fields, including finance, healthcare, environmental science, and engineering. Time-series data is critical for understanding and predicting patterns over time, yet traditional methods often fall short in handling the complex, dynamic, and large-scale nature of modern time-series datasets.\u003C/p>","\u003Cp style=\"text-align:justify;\">This special session seeks to bring together researchers and practitioners to discuss and explore the latest advancements in theories, methodologies, and applications that push the boundaries of time-series data analysis. The increasing prevalence and availability of high-dimensional time-series data demand innovative approaches that go beyond classical models. Traditional methods, while effective in certain scenarios, often struggle with non-linearity, non-stationarity, and missing or noisy data, which are common in real-world applications. Moreover, the rise of AI-driven techniques such as deep learning and neural networks has opened up new possibilities for extracting more nuanced insights from time-series data, yet many challenges remain unsolved. This special session is motivated by the need to systematically address these challenges and foster novel solutions that advance the state-of-the-art in time-series analysis. \u003C/p>\u003Cp style=\"text-align:justify;\">This session aims to: \u003Cbr>i) Provide a platform for presenting cutting-edge theories, models, and algorithms specifically designed for time-series data, including, but not limited to, novel deep learning architectures, statistical models, and hybrid approaches. ii) Highlight innovative applications of time-series methods in various domains, illustrating how these advancements contribute to real-world problem-solving and decision-making. iii) Promote interdisciplinary collaboration by inviting contributions from researchers across fields, fostering knowledge exchange that can drive future innovations in time-series data analysis. iv) Encourage discussions on challenges and limitations in the current approaches, opening avenues for future research.\u003C/p>","2024-12-13T23:44:22.653Z","2024-12-14T00:00:27.058Z","2024-12-14T00:00:27.046Z","413",[1226,1234,1242,1250,1258],{"id":1227,"name":1228,"committee":16,"position":16,"affiliation":1229,"email":16,"biography":16,"createdAt":1230,"updatedAt":1230,"url_path_id":1231,"contactPhoto":16,"socialLinks":1232,"url_path":1233},319,"Jia Guo","HBUE","2024-12-13T23:37:50.850Z","370",[],"-166",{"id":1235,"name":1236,"committee":16,"position":16,"affiliation":1237,"email":16,"biography":16,"createdAt":1238,"updatedAt":1238,"url_path_id":1239,"contactPhoto":16,"socialLinks":1240,"url_path":1241},320,"Jiacheng Li","Kanagawa University","2024-12-13T23:37:51.308Z","371",[],"-167",{"id":1243,"name":1244,"committee":16,"position":16,"affiliation":1245,"email":16,"biography":63,"createdAt":1246,"updatedAt":1246,"url_path_id":1247,"contactPhoto":16,"socialLinks":1248,"url_path":1249},360,"Tiezhu Shi","Shenzhen University","2024-12-13T23:59:41.286Z","479",[],"-274",{"id":1251,"name":1252,"committee":16,"position":16,"affiliation":1253,"email":16,"biography":63,"createdAt":1254,"updatedAt":1254,"url_path_id":1255,"contactPhoto":16,"socialLinks":1256,"url_path":1257},361,"Yuji Sato","Hosei University","2024-12-13T23:59:55.512Z","480",[],"-275",{"id":1259,"name":1260,"committee":16,"position":16,"affiliation":1261,"email":16,"biography":63,"createdAt":1262,"updatedAt":1262,"url_path_id":1263,"contactPhoto":16,"socialLinks":1264,"url_path":1265},362,"Zhiwei Ye","Hubei University of Technology","2024-12-14T00:00:08.985Z","481",[],"-276","-209",{"id":292,"session":1268},{"id":292,"title":1269,"teaser":1270,"body":1271,"createdAt":1272,"updatedAt":1273,"publishedAt":1274,"url_path_id":1275,"contacts":1276,"url_path":1293},"Advancing Physics-Informed Neural Networks: Bridging Scientific Principles and Machine Learning for Complex Systems","\u003Cp style=\"text-align:justify;\">The proposed special session, \"Advancing Physics-Informed Neural Networks (PINNs): Bridging Scientific Principles and Machine Learning for Complex Systems,\" aims to explore the latest developments, challenges, and applications of PINNs, a rapidly evolving paradigm at the intersection of computational science, physics, and artificial intelligence. PINNs leverage the synergy between data-driven approaches and physical laws, embedding domain knowledge into neural networks to solve complex problems in scientific computing.\u003C/p>","\u003Cp style=\"text-align:justify;\">This session seeks to bring together a diverse community of researchers and practitioners to address critical topics, including advancements in PINN architectures, theoretical foundations, scalability for large-scale problems, and integration with emerging technologies such as quantum computing and edge AI. Motivated by the growing need for interpretable, efficient, and generalizable machine learning models in engineering, healthcare, and climate science, this session will emphasize the transformative potential of PINNs in tackling real-world challenges. Contributions will highlight novel methodologies, such as adaptive training strategies, uncertainty quantification, and hybrid data-physics frameworks. Special attention will be given to interdisciplinary applications, ranging from fluid dynamics and structural mechanics to geophysics and biomedical engineering.\u003C/p>","2024-12-13T23:44:23.243Z","2024-12-14T00:02:25.056Z","2024-12-14T00:02:25.051Z","414",[1277,1285],{"id":1278,"name":1279,"committee":16,"position":16,"affiliation":1280,"email":16,"biography":63,"createdAt":1281,"updatedAt":1281,"url_path_id":1282,"contactPhoto":16,"socialLinks":1283,"url_path":1284},363,"Vincenzo Randazzo","Politecnico di Torino","2024-12-14T00:02:14.823Z","482",[],"-277",{"id":1286,"name":1287,"committee":16,"position":16,"affiliation":1288,"email":16,"biography":16,"createdAt":1289,"updatedAt":1289,"url_path_id":1290,"contactPhoto":16,"socialLinks":1291,"url_path":1292},300,"Giansalvo Cirrincione","University of Picardie Jules Verne","2024-12-13T23:37:42.846Z","351",[],"-147","-210",{"id":312,"session":1295},{"id":312,"title":1296,"teaser":1297,"body":1298,"createdAt":1299,"updatedAt":1300,"publishedAt":1301,"url_path_id":1302,"contacts":1303,"url_path":1334},"Advancing Structural Engineering with Neural Networks and AI: Design, Assessment, and Optimization","\u003Cp style=\"text-align:justify;\">This special section seeks to explore the transformative role of neural networks, in advancing the design, analysis, and resilience of engineering structures. Neural networks, with their ability to model complex, nonlinear relationships, have become indispensable tools in structural engineering. They are being increasingly integrated into engineering workflows, driving innovation in structural design, safety evaluation, and predictive maintenance. \u003C/p>","\u003Cp style=\"text-align:justify;\">The symposium will focus on groundbreaking studies that leverage Deep Learning (DL) and Machine Learning (ML) models, including but not limited to Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), and Transformer-based architectures. These techniques enable the engineering community to move beyond conventional analysis paradigms, offering robust, data-driven solutions for some of the most pressing challenges in the field. The goal of this session is to foster interdisciplinary dialogue, generate new ideas, and establish collaborations. It also aims to showcase how integrating neural networks and AI into engineering mechanics can make processes more efficient, sustainable, and accurate, while addressing safety and resilience in the face of natural hazards and evolving infrastructure demands.\u003C/p>","2024-12-13T23:44:23.835Z","2024-12-14T00:04:35.188Z","2024-12-14T00:04:35.183Z","415",[1304,1311,1313,1320,1327],{"id":1305,"name":1306,"committee":16,"position":16,"affiliation":1280,"email":16,"biography":16,"createdAt":1307,"updatedAt":1307,"url_path_id":1308,"contactPhoto":16,"socialLinks":1309,"url_path":1310},303,"Giuseppe Carlo Marano","2024-12-13T23:37:43.965Z","354",[],"-150",{"id":1286,"name":1287,"committee":16,"position":16,"affiliation":1288,"email":16,"biography":16,"createdAt":1289,"updatedAt":1289,"url_path_id":1290,"contactPhoto":16,"socialLinks":1312,"url_path":1292},[],{"id":1314,"name":1315,"committee":16,"position":16,"affiliation":1280,"email":16,"biography":16,"createdAt":1316,"updatedAt":1316,"url_path_id":1317,"contactPhoto":16,"socialLinks":1318,"url_path":1319},356,"Marco Martino Rosso","2024-12-13T23:38:10.262Z","407",[],"-203",{"id":1321,"name":1322,"committee":16,"position":16,"affiliation":1280,"email":16,"biography":16,"createdAt":1323,"updatedAt":1323,"url_path_id":1324,"contactPhoto":16,"socialLinks":1325,"url_path":1326},340,"Laura Sardone","2024-12-13T23:38:00.633Z","391",[],"-187",{"id":1328,"name":1329,"committee":16,"position":16,"affiliation":1280,"email":16,"biography":16,"createdAt":1330,"updatedAt":1330,"url_path_id":1331,"contactPhoto":16,"socialLinks":1332,"url_path":1333},328,"Jonathan Melchiorre","2024-12-13T23:37:54.849Z","379",[],"-175","-211",{"id":1336,"session":1337},85,{"id":533,"title":1338,"teaser":1339,"body":1340,"createdAt":1341,"updatedAt":1342,"publishedAt":1343,"url_path_id":1344,"contacts":1345,"url_path":1377},"AI-Driven Revolution in Healthcare: Exploring Foundation Models and Their Applications","\u003Cp style=\"text-align:justify;\">The healthcare domain is undergoing a transformative revolution driven by the adoption of artificial intelligence (AI) technologies, among which Foundation Models (FMs) are emerging as game changers. Foundation Models, encompassing large-scale pre-trained models like GPT-4, BERT, and others, offer a unified approach to dealing with a multitude of tasks by leveraging extensive pretraining on diverse datasets. \u003C/p>","\u003Cp style=\"text-align:justify;\">This special session aims to bring together researchers, practitioners, and industry experts to explore the potentials and challenges of applying FMs in healthcare, thereby advancing both AI techniques and their impactful applications. The rapid evolution of FMs holds considerable promise for healthcare applications. FMs can address complex healthcare tasks, including diagnosis, medical image analysis, electronic health record (EHR) processing, and personalized treatment planning, with improved accuracy and efficiency. However, applying FMs in healthcare settings poses unique challenges, such as data privacy, model interpretability, regulatory compliance, and clinical validation. The motivation for this session lies in tackling these challenges by creating a platform for experts to share their insights, fostering collaboration among the stakeholders in academia, healthcare, and industry. \u003C/p>\u003Cp style=\"text-align:justify;\">The primary objective of this session is to discuss the development, adaptation, and deployment of FMs tailored specifically for healthcare applications. We aim to cover multiple facets of FMs, including model architectures, learning paradigms, fine-tuning methodologies, and their clinical evaluations. Moreover, we intend to address ethical and legal implications, emphasizing trustworthiness, interpretability, and privacy concerns, thereby accelerating the safe adoption of these models in the healthcare domain. The novelty of this special session lies in focusing on the intersection of FMs and healthcare while addressing both technical advancements and real-world implementation barriers. Although FMs have been well explored in general domains like language understanding and image recognition, their deployment in healthcare is less mature. This session will provide an innovative perspective by spotlighting pioneering research, domain adaptation strategies, and challenges unique to medical applications that have yet to be fully addressed by the AI research community. As IJCNN 2025 seeks to bring cutting-edge developments in AI and neural networks to the forefront, this special session is of great relevance to the conference theme. The application of neural-based Foundation Models in healthcare aligns with IJCNN’s focus on impactful, transformative research and real-world applications. This session will present state-of-the-art findings that illustrate how advances in neural architectures can lead to breakthroughs in medical diagnostics, clinical decision support, and precision medicine. The potential impact of FMs in healthcare is enormous. \u003C/p>\u003Cp style=\"text-align:justify;\">By empowering healthcare professionals with AI-driven tools that enhance diagnostic accuracy and streamline clinical workflows, these models can significantly improve patient outcomes and reduce costs. Moreover, the session will explore the societal benefits of democratizing healthcare AI, enabling underserved populations to gain access to quality healthcare through scalable, model-based solutions. By addressing technical, ethical, and regulatory hurdles, the discussions in this session will contribute to building a framework for safe, fair, and equitable adoption of FMs in healthcare, ultimately bridging the gap between research and practice. Through this special session, we hope to foster a community dedicated to overcoming the technical and societal challenges of adopting FMs in healthcare, thereby pushing the frontiers of AI and ensuring its positive impact on one of the most critical domains—human health.\u003C/p>","2024-12-13T23:44:25.096Z","2024-12-14T00:21:15.010Z","2024-12-14T00:21:15.004Z","417",[1346,1354,1362,1370],{"id":1347,"name":1348,"committee":16,"position":16,"affiliation":1349,"email":16,"biography":63,"createdAt":1350,"updatedAt":1350,"url_path_id":1351,"contactPhoto":16,"socialLinks":1352,"url_path":1353},368,"Xueping Peng","University of Technology Sydney","2024-12-14T00:20:37.267Z","487",[],"-282",{"id":1355,"name":1356,"committee":16,"position":16,"affiliation":1357,"email":16,"biography":63,"createdAt":1358,"updatedAt":1358,"url_path_id":1359,"contactPhoto":16,"socialLinks":1360,"url_path":1361},369,"Tianyi Zhou","University of Maryland","2024-12-14T00:20:50.812Z","488",[],"-283",{"id":1363,"name":1364,"committee":16,"position":16,"affiliation":1365,"email":16,"biography":16,"createdAt":1366,"updatedAt":1366,"url_path_id":1367,"contactPhoto":16,"socialLinks":1368,"url_path":1369},256,"Chengqi Zhang","The Hong Kong Polytechnic University","2024-12-13T23:37:28.490Z","307",[],"-103",{"id":1371,"name":1372,"committee":16,"position":16,"affiliation":1349,"email":16,"biography":16,"createdAt":1373,"updatedAt":1373,"url_path_id":1374,"contactPhoto":16,"socialLinks":1375,"url_path":1376},306,"Guodong Long","2024-12-13T23:37:45.170Z","357",[],"-153","-213",{"id":14,"session":1379},{"id":14,"title":1380,"teaser":1381,"body":1382,"createdAt":1383,"updatedAt":1384,"publishedAt":1385,"url_path_id":1386,"contacts":1387,"url_path":1426},"AI for Social Good","\u003Cp style=\"text-align:justify;\">The potential of AI extends far beyond commercial applications, with a profound capability to address pressing societal challenges. From mitigating climate change and improving healthcare access to reducing poverty and enhancing education, AI has the power to create tangible benefits for humanity. \u003C/p>","\u003Cp style=\"text-align:justify;\">However, significant gaps remain in aligning AI methods with social good initiatives, particularly in underrepresented areas such as disaster response, environmental sustainability, and equitable resource distribution. The challenge lies not only in developing AI technologies but in deploying them ethically, equitably, and effectively to address these critical issues.\u003C/p>","2024-12-13T23:44:24.478Z","2024-12-14T00:17:57.036Z","2024-12-14T00:17:57.031Z","416",[1388,1396,1403,1411,1419],{"id":1389,"name":1390,"committee":16,"position":16,"affiliation":1391,"email":16,"biography":63,"createdAt":1392,"updatedAt":1392,"url_path_id":1393,"contactPhoto":16,"socialLinks":1394,"url_path":1395},364,"Rui Mao","Nanyang Technological University","2024-12-14T00:16:47.988Z","483",[],"-278",{"id":1397,"name":1398,"committee":16,"position":16,"affiliation":1391,"email":16,"biography":63,"createdAt":1399,"updatedAt":1399,"url_path_id":1400,"contactPhoto":16,"socialLinks":1401,"url_path":1402},365,"Xulang Zhang","2024-12-14T00:17:03.258Z","484",[],"-279",{"id":1404,"name":1405,"committee":16,"position":16,"affiliation":1406,"email":16,"biography":63,"createdAt":1407,"updatedAt":1407,"url_path_id":1408,"contactPhoto":16,"socialLinks":1409,"url_path":1410},366,"Zhaoxia Wang","Singapore Management University","2024-12-14T00:17:18.625Z","485",[],"-280",{"id":1412,"name":1413,"committee":16,"position":16,"affiliation":1414,"email":16,"biography":63,"createdAt":1415,"updatedAt":1415,"url_path_id":1416,"contactPhoto":16,"socialLinks":1417,"url_path":1418},367,"Seng-Beng Ho","Agency for Science, Technology and Research","2024-12-14T00:17:33.113Z","486",[],"-281",{"id":1420,"name":1421,"committee":16,"position":16,"affiliation":1391,"email":16,"biography":16,"createdAt":1422,"updatedAt":1422,"url_path_id":1423,"contactPhoto":16,"socialLinks":1424,"url_path":1425},279,"Erik Cambria","2024-12-13T23:37:35.672Z","330",[],"-126","-212",{"id":533,"session":1428},{"id":594,"title":1429,"teaser":1430,"body":1431,"createdAt":1432,"updatedAt":1433,"publishedAt":1434,"url_path_id":1435,"contacts":1436,"url_path":1500},"AI, Law and Regulation","\u003Cp style=\"text-align:justify;\">Breakthroughs in Artificial Intelligence (AI) are increasingly permeating everyday life, reshaping sectors such as the economy, medicine, military, education, and creative industries. As global powerhouses strive to foster innovation and attract investment, they are also enacting regulations to safeguard the interests, rights, and freedoms of their citizens. Consequently, the ethical and regulatory challenges across the AI value chain—spanning design, development, and deployment—are now at the forefront of legal and policy debates.\u003C/p>","\u003Cp style=\"text-align:justify;\">Bridging the interdisciplinary gap between AI developers and the socio-legal dimensions of AI is critical to understanding the foreseeable legislative changes and their impact on AI pioneers. Whether considering discriminative or generative models, it is essential to compare existing rules, challenges, and compliance requirements with the technical capabilities and limitations of system architectures. This special session aims to connect key legal and ethical perspectives on governance frameworks for AI, addressing regulatory considerations, AI standards, and best practices. Particular attention is given to EU regulations, such as the AI Act and GDPR etc., which serve as significant points of reference for responsible innovation and regulatory compliance across industries, inspiring similar frameworks in other regions. However, this session strongly encourages contributions exploring non-EU laws and regulations that influence AI’s systems design and implementation. We seek contributions that reduce the gaps between system architecture design, model inputs and outputs, and their legal implications.\u003C/p>","2024-12-13T23:44:25.649Z","2024-12-16T19:34:17.268Z","2024-12-16T19:34:17.262Z","418",[1437,1445,1484,1492],{"id":1438,"name":1439,"committee":16,"position":16,"affiliation":1440,"email":16,"biography":16,"createdAt":1441,"updatedAt":1441,"url_path_id":1442,"contactPhoto":16,"socialLinks":1443,"url_path":1444},233,"Amanda Horzyk","University of Edinburgh","2024-12-13T23:37:21.762Z","284",[],"-80",{"id":433,"name":1446,"committee":16,"position":16,"affiliation":1447,"email":16,"biography":63,"createdAt":1448,"updatedAt":1449,"url_path_id":1450,"contactPhoto":1451,"socialLinks":1479,"url_path":1483},"Nicola Fabiano","Studio Legale Fabiano - UNU AI Network","2024-11-07T18:53:43.708Z","2024-11-07T19:46:52.346Z","79",{"id":1452,"name":1453,"alternativeText":16,"caption":16,"width":1454,"height":1455,"formats":1456,"hash":1475,"ext":1029,"mime":1032,"size":1476,"url":1477,"previewUrl":16,"provider":23,"provider_metadata":16,"createdAt":1478,"updatedAt":1478},120,"foto nicola.jpg",817,923,{"small":1457,"medium":1463,"thumbnail":1469},{"ext":1029,"url":1458,"hash":1459,"mime":1032,"name":1460,"path":16,"size":1461,"width":1462,"height":913},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/small_foto_nicola_757df45fd9.jpg","small_foto_nicola_757df45fd9","small_foto nicola.jpg",24.02,443,{"ext":1029,"url":1464,"hash":1465,"mime":1032,"name":1466,"path":16,"size":1467,"width":1468,"height":920},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/medium_foto_nicola_757df45fd9.jpg","medium_foto_nicola_757df45fd9","medium_foto nicola.jpg",43.14,664,{"ext":1029,"url":1470,"hash":1471,"mime":1032,"name":1472,"path":16,"size":1473,"width":1474,"height":1047},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/thumbnail_foto_nicola_757df45fd9.jpg","thumbnail_foto_nicola_757df45fd9","thumbnail_foto nicola.jpg",4.05,138,"foto_nicola_757df45fd9",58.12,"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/foto_nicola_757df45fd9.jpg","2024-11-07T19:18:00.241Z",[1480],{"id":201,"url":1481,"platform":1482},"https://www.fabiano.law/it/","Website","-42",{"id":1485,"name":1486,"committee":16,"position":16,"affiliation":1487,"email":16,"biography":16,"createdAt":1488,"updatedAt":1488,"url_path_id":1489,"contactPhoto":16,"socialLinks":1490,"url_path":1491},246,"Asim Roy","University of Arizona","2024-12-13T23:37:25.587Z","297",[],"-93",{"id":1493,"name":1494,"committee":16,"position":16,"affiliation":1495,"email":16,"biography":16,"createdAt":1496,"updatedAt":1496,"url_path_id":1497,"contactPhoto":16,"socialLinks":1498,"url_path":1499},352,"Maja Nisevic","KU Leuven Centre for IT & IP Law (CiTiP","2024-12-13T23:38:07.770Z","403",[],"-199","-214",{"id":594,"session":1502},{"id":226,"title":1503,"teaser":1504,"body":1505,"createdAt":1506,"updatedAt":1507,"publishedAt":1508,"url_path_id":1509,"contacts":1510,"url_path":1569},"AICS: Artificial Intelligence for Complex Systems","\u003Cp>The special session aims to explore the challenging relationship between Artificial Intelligence (AI) and complex systems through Complexity Theory, delving into the understanding of modern AI systems such as deep learning architectures and large language models (e.g., GPT/ChatGPT, Gemini, Llama, Claude, etc.) as complex dynamic systems. \u003C/p>","\u003Cp>With a multidisciplinary focus on stochastic processes, explainable AI, cognitive approaches, multimodal learning, AI and security, and AI and bias, the session will serve as a multidisciplinary platform that extends beyond engineering to include cognitive science, (computational) linguistics, philosophy, and other relevant fields. Specifically, we welcome researchers and engineers in AI and complex systems theory, cognitive scientists, linguists, and philosophers as well as industry professionals seeking to apply complexity theory in AI solutions to submit their works to this special session on the following four objectives: \u003Cbr> \u003C/p>\u003Cp style=\"margin-left:40px;\">i) To investigate how Complexity Theory can offer invaluable tools for analyzing AI systems, particularly in the context of dynamic behavior, emergent properties, and stochastic processes. \u003Cbr>\u003Cbr>ii) To explore how AI can be employed to study and understand complex systems, including information granulation (Granular Computing) and multi-agent environments. \u003Cbr>\u003Cbr>iii) To establish new methodologies for measuring the intelligence and linguistic understanding of AI systems through the lens of Complexity Theory. \u003Cbr>\u003Cbr>iv) To discuss the future directions and next steps in the intersection of AI and Complexity Theory in reaching artificial general intelligence (AGI).\u003C/p>","2024-12-13T23:44:26.243Z","2025-01-30T18:39:00.617Z","2024-12-16T19:36:39.133Z","419",[1511,1519,1527],{"id":1512,"name":1513,"committee":16,"position":16,"affiliation":1514,"email":16,"biography":16,"createdAt":1515,"updatedAt":1515,"url_path_id":1516,"contactPhoto":16,"socialLinks":1517,"url_path":1518},230,"Alessio Martino","LUISS University","2024-12-13T23:37:20.983Z","281",[],"-77",{"id":1520,"name":1521,"committee":16,"position":16,"affiliation":1522,"email":16,"biography":16,"createdAt":1523,"updatedAt":1523,"url_path_id":1524,"contactPhoto":16,"socialLinks":1525,"url_path":1526},276,"Enrico De Santis","Sapienza University of Rome","2024-12-13T23:37:34.706Z","327",[],"-123",{"id":359,"name":1528,"committee":16,"position":16,"affiliation":1522,"email":16,"biography":63,"createdAt":1529,"updatedAt":1529,"url_path_id":1530,"contactPhoto":1531,"socialLinks":1565,"url_path":1568},"Antonello Rizzi","2024-11-07T18:59:00.438Z","82",{"id":1532,"name":1533,"alternativeText":16,"caption":16,"width":1534,"height":1535,"formats":1536,"hash":1561,"ext":1029,"mime":1032,"size":1562,"url":1563,"previewUrl":16,"provider":23,"provider_metadata":16,"createdAt":1564,"updatedAt":1564},119,"1pVyMGgTmhmVQNHac7ZaDDFB6rk6DxEqSaSHHU-8_fe5UOFYK6g.jpg",1225,1230,{"large":1537,"small":1543,"medium":1549,"thumbnail":1555},{"ext":1029,"url":1538,"hash":1539,"mime":1032,"name":1540,"path":16,"size":1541,"width":1542,"height":906},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/large_1p_Vy_M_Gg_Tmhm_VQN_Hac7_Za_DDFB_6rk6_Dx_Eq_Sa_SHHU_8_fe5_UOFYK_6g_a622b84af8.jpg","large_1p_Vy_M_Gg_Tmhm_VQN_Hac7_Za_DDFB_6rk6_Dx_Eq_Sa_SHHU_8_fe5_UOFYK_6g_a622b84af8","large_1pVyMGgTmhmVQNHac7ZaDDFB6rk6DxEqSaSHHU-8_fe5UOFYK6g.jpg",86.88,996,{"ext":1029,"url":1544,"hash":1545,"mime":1032,"name":1546,"path":16,"size":1547,"width":1548,"height":913},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/small_1p_Vy_M_Gg_Tmhm_VQN_Hac7_Za_DDFB_6rk6_Dx_Eq_Sa_SHHU_8_fe5_UOFYK_6g_a622b84af8.jpg","small_1p_Vy_M_Gg_Tmhm_VQN_Hac7_Za_DDFB_6rk6_Dx_Eq_Sa_SHHU_8_fe5_UOFYK_6g_a622b84af8","small_1pVyMGgTmhmVQNHac7ZaDDFB6rk6DxEqSaSHHU-8_fe5UOFYK6g.jpg",26.2,498,{"ext":1029,"url":1550,"hash":1551,"mime":1032,"name":1552,"path":16,"size":1553,"width":1554,"height":920},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/medium_1p_Vy_M_Gg_Tmhm_VQN_Hac7_Za_DDFB_6rk6_Dx_Eq_Sa_SHHU_8_fe5_UOFYK_6g_a622b84af8.jpg","medium_1p_Vy_M_Gg_Tmhm_VQN_Hac7_Za_DDFB_6rk6_Dx_Eq_Sa_SHHU_8_fe5_UOFYK_6g_a622b84af8","medium_1pVyMGgTmhmVQNHac7ZaDDFB6rk6DxEqSaSHHU-8_fe5UOFYK6g.jpg",49.38,747,{"ext":1029,"url":1556,"hash":1557,"mime":1032,"name":1558,"path":16,"size":1559,"width":1560,"height":1047},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/thumbnail_1p_Vy_M_Gg_Tmhm_VQN_Hac7_Za_DDFB_6rk6_Dx_Eq_Sa_SHHU_8_fe5_UOFYK_6g_a622b84af8.jpg","thumbnail_1p_Vy_M_Gg_Tmhm_VQN_Hac7_Za_DDFB_6rk6_Dx_Eq_Sa_SHHU_8_fe5_UOFYK_6g_a622b84af8","thumbnail_1pVyMGgTmhmVQNHac7ZaDDFB6rk6DxEqSaSHHU-8_fe5UOFYK6g.jpg",4.66,155,"1p_Vy_M_Gg_Tmhm_VQN_Hac7_Za_DDFB_6rk6_Dx_Eq_Sa_SHHU_8_fe5_UOFYK_6g_a622b84af8",130.3,"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/1p_Vy_M_Gg_Tmhm_VQN_Hac7_Za_DDFB_6rk6_Dx_Eq_Sa_SHHU_8_fe5_UOFYK_6g_a622b84af8.jpg","2024-11-07T18:58:58.122Z",[1566],{"id":427,"url":1567,"platform":1482},"https://antonellorizzi.site.uniroma1.it/","-45","-215",{"id":226,"session":1571},{"id":514,"title":1572,"teaser":1573,"body":1574,"createdAt":1575,"updatedAt":1576,"publishedAt":1577,"url_path_id":1578,"contacts":1579,"url_path":1613},"Application of Explainable Neural Network Models in Processing and Analysis of Neuronal Data","\u003Cp style=\"text-align:justify;\">The field of neuroscience is experiencing a data revolution, driven by advances in recording and imaging technologies that generate complex and high-dimensional neuronal datasets. \u003C/p>","\u003Cp style=\"text-align:justify;\">These datasets hold the potential to reveal important insights about brain function, cognition, and neurological disorders. However, traditional computational methods often fall short of handling this complexity, while traditional artificial intelligence (AI) models, such as, deep learning, despite their power, are criticised for their lack of interpretability – a major barrier in fields like neuroscience where transparency is essential. \u003Cbr>\u003Cbr>Explainable Neural Network (XNN) models address this challenge by coupling the predictive capabilities of deep learning with mechanisms for interpretability, making them a transformative tool for neuronal data analysis. The proposed special session at IJCNN 2025 focuses on the motivations, advancements, and implications of applying XNNs to process and analyse neuronal data, aligning with the conference’s themes of ‘Human-AI interaction’. By focusing on explainability, this session aims to foster trust and transparency in AI applications to increase human interaction, a priority in neuroscience research and healthcare.\u003C/p>","2024-12-13T23:44:26.813Z","2024-12-16T19:39:39.848Z","2024-12-16T19:39:39.842Z","420",[1580,1588,1596,1605],{"id":1581,"name":1582,"committee":16,"position":16,"affiliation":1583,"email":16,"biography":63,"createdAt":1584,"updatedAt":1584,"url_path_id":1585,"contactPhoto":16,"socialLinks":1586,"url_path":1587},371,"Mufti Mahmud","Nottingham Trent University","2024-12-16T19:39:19.625Z","490",[],"-285",{"id":1589,"name":1590,"committee":16,"position":16,"affiliation":1591,"email":16,"biography":16,"createdAt":1592,"updatedAt":1592,"url_path_id":1593,"contactPhoto":16,"socialLinks":1594,"url_path":1595},290,"Francesco Carlo Morabito","University Mediterranea of Reggio Calabria","2024-12-13T23:37:39.334Z","341",[],"-137",{"id":1597,"name":1598,"committee":16,"position":16,"affiliation":1599,"email":16,"biography":63,"createdAt":1600,"updatedAt":1601,"url_path_id":1602,"contactPhoto":16,"socialLinks":1603,"url_path":1604},370,"Maryam Doborjeh","Auckland University of Technology","2024-12-16T19:38:59.201Z","2024-12-16T19:39:02.815Z","489",[],"-284",{"id":1606,"name":1607,"committee":16,"position":16,"affiliation":1608,"email":16,"biography":16,"createdAt":1609,"updatedAt":1609,"url_path_id":1610,"contactPhoto":16,"socialLinks":1611,"url_path":1612},350,"M Shamim Kaiser","Jahangirnagar University","2024-12-13T23:38:06.740Z","401",[],"-197","-216",{"id":514,"session":1615},{"id":161,"title":1616,"teaser":1617,"body":1618,"createdAt":1619,"updatedAt":1620,"publishedAt":1621,"url_path_id":1622,"contacts":1623,"url_path":1632},"Artificial Intelligence and Machine Learning Innovations: Showcasing Funded European Projects","\u003Cp style=\"text-align:justify;\">In recent years, the European Commission has significantly increased its investment in Artificial Intelligence (AI) and Machine Learning (ML) research as part of its strategy to position Europe as a global leader in digital innovation.\u003C/p>","\u003Cp style=\"text-align:justify;\">Through initiatives like Horizon Europe and the Digital Europe Programme, billions of euros have been allocated to support collaborative projects that harness the transformative power of AI and ML to address critical societal, economic, and environmental challenges. Key areas of focus include fostering sustainable development, advancing healthcare technologies, boosting industrial competitiveness, and enhancing digital sovereignty. Notably, the Commission's efforts prioritize ethical AI development and the promotion of trustworthy and inclusive technologies aligned with European values. \u003Cbr>\u003Cbr>This Special Session aims to showcase the most innovative and impactful projects funded under these frameworks, offering a platform for the dissemination of results and the exchange of ideas. Contributors are encouraged to present their achievements and share lessons learned, with the goal of inspiring further advancements and collaborations in the field. This Special Session aims to bring together researchers, practitioners, and innovators to present and discuss the outcomes of European projects funded by the European Commission that leverage advanced Artificial Intelligence (AI) and Machine Learning (ML) techniques. Selected contributions will provide insights into cutting-edge solutions developed in areas such as healthcare, energy, Industry 4.0, sustainable mobility, smart agriculture, and digital governance. \u003Cbr>\u003Cbr>The session's objective is to highlight the role of AI and ML in addressing global challenges, fostering digital transformation, sustainability, and social inclusion. We invite authors to submit reports on case studies, innovative methodologies, developed platforms, and the socio-economic impacts of their projects.\u003C/p>","2024-12-13T23:44:27.367Z","2024-12-16T19:41:41.916Z","2024-12-16T19:41:41.910Z","421",[1624,1630],{"id":1625,"name":1528,"committee":16,"position":16,"affiliation":1522,"email":16,"biography":16,"createdAt":1626,"updatedAt":1626,"url_path_id":1627,"contactPhoto":16,"socialLinks":1628,"url_path":1629},243,"2024-12-13T23:37:24.756Z","294",[],"-90",{"id":1520,"name":1521,"committee":16,"position":16,"affiliation":1522,"email":16,"biography":16,"createdAt":1523,"updatedAt":1523,"url_path_id":1524,"contactPhoto":16,"socialLinks":1631,"url_path":1526},[],"-217",{"id":161,"session":1634},{"id":730,"title":1635,"teaser":1636,"body":1637,"createdAt":1638,"updatedAt":1639,"publishedAt":1640,"url_path_id":1641,"contacts":1642,"url_path":1690},"Artificial Intelligence for Neural Engineering: Innovations, Applications and Future Directions","\u003Cp style=\"text-align:justify;\">The proposed special session will serve as a premier platform for researchers, practitioners, and industry experts to present innovations, share insights, and discuss future trends in the rapidly evolving intersection of artificial intelligence (AI) and neural engineering. \u003C/p>","\u003Cp style=\"text-align:justify;\">AI and neural engineering represent transformative areas of research. Advances in machine learning have revolutionized how neural systems are modeled and understood, with applications spanning diagnosis, brain-computer interfaces (BCIs), neuroprosthetics, and neurorehabilitation. Despite these breakthroughs, challenges persist in developing algorithms that can handle complex, variable neural data in real time while maintaining transparency and interpretability, especially in healthcare contexts. \u003C/p>\u003Cp style=\"text-align:justify;\">The proposed special session aims to:\u003C/p>\u003Cp style=\"text-align:justify;\">i)  foster innovation by encouraging novel AI techniques tailored for neural engineering applications, such as signal processing, neuroimaging analysis, and cognitive modeling. \u003C/p>\u003Cp style=\"text-align:justify;\">ii) bridge theory and practice by showcasing theoretical advances in AI, alongside real-world applications in clinical and neurotechnological settings. \u003C/p>\u003Cp style=\"text-align:justify;\">iii) promote interdisciplinary collaboration, connecting experts from AI, neuroscience, neurology, biomedical engineering, and related fields to share knowledge and forge new collaborations.\u003C/p>","2024-12-13T23:44:27.964Z","2024-12-16T19:45:52.845Z","2024-12-16T19:45:52.825Z","422",[1643,1651,1659,1666,1674,1682],{"id":1644,"name":1645,"committee":16,"position":16,"affiliation":1646,"email":16,"biography":63,"createdAt":1647,"updatedAt":1647,"url_path_id":1648,"contactPhoto":16,"socialLinks":1649,"url_path":1650},372,"Nadia Mammone","University of Reggio Calabria","2024-12-16T19:43:57.478Z","491",[],"-286",{"id":1652,"name":1653,"committee":16,"position":16,"affiliation":1654,"email":16,"biography":63,"createdAt":1655,"updatedAt":1655,"url_path_id":1656,"contactPhoto":16,"socialLinks":1657,"url_path":1658},373,"Sergi Abadal","Universitat Politècnica de Catalunya (UPC)","2024-12-16T19:44:13.644Z","492",[],"-287",{"id":1660,"name":1661,"committee":16,"position":16,"affiliation":1591,"email":16,"biography":16,"createdAt":1662,"updatedAt":1662,"url_path_id":1663,"contactPhoto":16,"socialLinks":1664,"url_path":1665},261,"Cosimo Ieracitano","2024-12-13T23:37:29.915Z","312",[],"-108",{"id":1667,"name":1668,"committee":16,"position":16,"affiliation":1669,"email":16,"biography":63,"createdAt":1670,"updatedAt":1670,"url_path_id":1671,"contactPhoto":16,"socialLinks":1672,"url_path":1673},374,"Toshihisa Tanaka","Tokyo University of Agriculture and Technology","2024-12-16T19:44:34.756Z","493",[],"-288",{"id":1675,"name":1676,"committee":16,"position":16,"affiliation":1677,"email":16,"biography":63,"createdAt":1678,"updatedAt":1678,"url_path_id":1679,"contactPhoto":16,"socialLinks":1680,"url_path":1681},375,"Yiwen Wang","Hong Kong University of Science and Technology","2024-12-16T19:44:49.799Z","494",[],"-289",{"id":1683,"name":1684,"committee":16,"position":16,"affiliation":1685,"email":16,"biography":63,"createdAt":1686,"updatedAt":1686,"url_path_id":1687,"contactPhoto":16,"socialLinks":1688,"url_path":1689},376,"Xiang Zhang","University of North Carolina (UNC)","2024-12-16T19:45:05.339Z","495",[],"-290","-218",{"id":730,"session":1692},{"id":750,"title":1693,"teaser":1694,"body":1695,"createdAt":1696,"updatedAt":1697,"publishedAt":1698,"url_path_id":1699,"contacts":1700,"url_path":1730},"Artificial Intelligence in Healthcare: Leveraging Transformer Models","\u003Cp style=\"text-align:justify;\">Artificial intelligence transformer-based models such as the BERT model (Bidirectional Encoder Representations from Transformers), GPT (Generative Pre-trained Transformer), vision transformers (ViT) and many others have found significant applications in healthcare. \u003C/p>","\u003Cp style=\"text-align:justify;\">These powerful models are based on the transformer architecture, which uses self-attention mechanisms to learn contextual relationships between input data. This makes them particularly well-suited for analysing complex and heterogeneous healthcare data, such as electronic health records (EHRs), medical images, and genomics data. One of the most promising applications of artificial intelligence transformer-based models in healthcare is in medical image analysis.\u003Cbr>\u003Cbr>Convolutional neural networks (CNNs) have been widely used for image analysis tasks, but they have limitations in processing large volumes of data due to the fixed-size receptive field. In contrast, transformer-based models can handle variable-sized inputs and learn more complex features from the image data. For example, transformer-based models have achieved state-of-the-art performance in tasks such as lesion segmentation, classification, and anomaly detection in medical imaging. Another important application of AI transformer-based models in healthcare is in natural language processing (NLP) tasks, particularly in analysing clinical notes and electronic health records (EHR). These documents contain large amounts of unstructured data, making it challenging to extract relevant information. \u003Cbr>\u003Cbr>However, transformer-based models can learn to extract semantic meaning from the text and make predictions based on that information. For instance, they can be used to predict patient outcomes or identify disease risk factors from EHRs. In addition to medical imaging and NLP, AI transformer-based models can also be used in genomics data analysis, drug discovery, and personalised medicine. Genomics data contains a large amount of variability, making it challenging to identify patterns and make accurate predictions. \u003Cbr>\u003Cbr>Transformer-based models can learn to capture complex relationships between genes and diseases, making it possible to identify new drug targets and develop personalised treatments. Furthermore, transformer-based models have been shown to be extremely effective in handling multi-modality data in healthcare applications, such as clinical text and image integration (e.g., Med-BERT, BioBert, etc.).\u003C/p>","2024-12-13T23:44:28.760Z","2024-12-16T19:50:00.349Z","2024-12-16T19:50:00.328Z","423",[1701,1708,1715,1722],{"id":1702,"name":1703,"committee":16,"position":16,"affiliation":1349,"email":16,"biography":63,"createdAt":1704,"updatedAt":1704,"url_path_id":1705,"contactPhoto":16,"socialLinks":1706,"url_path":1707},377,"Ali Braytree","2024-12-16T19:48:51.546Z","496",[],"-291",{"id":1709,"name":1710,"committee":16,"position":16,"affiliation":1349,"email":16,"biography":63,"createdAt":1711,"updatedAt":1711,"url_path_id":1712,"contactPhoto":16,"socialLinks":1713,"url_path":1714},378,"Mingshan Jia","2024-12-16T19:49:07.834Z","497",[],"-292",{"id":1716,"name":1717,"committee":16,"position":16,"affiliation":1349,"email":16,"biography":63,"createdAt":1718,"updatedAt":1718,"url_path_id":1719,"contactPhoto":16,"socialLinks":1720,"url_path":1721},379,"Mukesh Prasad","2024-12-16T19:49:22.583Z","498",[],"-293",{"id":1723,"name":1724,"committee":16,"position":16,"affiliation":1725,"email":16,"biography":63,"createdAt":1726,"updatedAt":1726,"url_path_id":1727,"contactPhoto":16,"socialLinks":1728,"url_path":1729},380,"Hai Yan Lu","University of Technology, Sydney","2024-12-16T19:49:38.941Z","499",[],"-294","-219",{"id":750,"session":1732},{"id":1733,"title":1734,"teaser":1735,"body":1736,"createdAt":1737,"updatedAt":1738,"publishedAt":1739,"url_path_id":1740,"contacts":1741,"url_path":1766},18,"Artificial Intelligence in Software Quality and Evolution","\u003Cp style=\"text-align:justify;\">The growing complexity of software systems and the constant need to adapt them to the changing needs of users and markets make constant software evolution essential. Therefore, the need to ensure quality and adaptability to software systems makes it urgent to integrate advanced solutions that can assist development teams in the evolutionary and maintenance process. \u003C/p>","\u003Cp>Developers must address timely defect identification, technical debt reduction, and maintenance planning to ensure reliable and safe performance. In this context, artificial intelligence (AI) emerges as an innovative and powerful resource, offering tools capable of analyzing large volumes of data, identifying hidden patterns, and supporting software evolutionary decisions with a high level of automation and precision. Despite the progress, the application of AI for software quality and evolution is still in an exploratory phase and presents great potential for development. Therefore, this special session was born to explore how AI can be integrated into software engineering practices to monitor, improve, and adapt software quality over time. Through the analysis of advanced AI-based methods, tools, and models, the session aims to propose practical solutions to identify, analyze, and reduce quality problems and to promote the continuous evolution of software systems. The mission is to bring together experts and researchers in the field of AI applied to software engineering to discuss innovative approaches and collaborate to build a shared vision of the role of AI in software evolution. This involvement aims to stimulate dialogue and collaboration to develop AI-based tools and methods that can improve the quality and sustainability of software projects, promoting more efficient development and focusing on the long-term reliability of software. The main topics cover key areas of AI applications to improve software quality and evolution. However, these topics do not represent a limit: the session is open to contributions exploring further innovative and multidisciplinary aspects.\u003C/p>","2024-12-13T23:44:29.547Z","2024-12-17T00:06:50.169Z","2024-12-17T00:06:50.162Z","424",[1742,1750,1758],{"id":1743,"name":1744,"committee":16,"position":16,"affiliation":1745,"email":16,"biography":16,"createdAt":1746,"updatedAt":1746,"url_path_id":1747,"contactPhoto":16,"socialLinks":1748,"url_path":1749},342,"Lerina Aversano","University of Foggia","2024-12-13T23:38:01.721Z","393",[],"-189",{"id":1751,"name":1752,"committee":16,"position":16,"affiliation":1753,"email":16,"biography":63,"createdAt":1754,"updatedAt":1754,"url_path_id":1755,"contactPhoto":16,"socialLinks":1756,"url_path":1757},381,"Martina Iammarino","University Pegaso","2024-12-17T00:06:39.518Z","500",[],"-295",{"id":1759,"name":1760,"committee":16,"position":16,"affiliation":1761,"email":16,"biography":16,"createdAt":1762,"updatedAt":1762,"url_path_id":1763,"contactPhoto":16,"socialLinks":1764,"url_path":1765},257,"Chiara Verdone","University of Sannio","2024-12-13T23:37:28.787Z","308",[],"-104","-220",{"id":1733,"session":1768},{"id":111,"title":1769,"teaser":1770,"body":1771,"createdAt":1772,"updatedAt":1773,"publishedAt":1774,"url_path_id":1775,"contacts":1776,"url_path":1801},"Bayesian Methods for Inference and Learning","\u003Cp style=\"text-align:justify;\">The development of intelligent systems capable of reasoning and learning under uncertainty is fundamental in several contexts. The Bayesian perspective provides a powerful framework for modeling complex dependencies and handling incomplete information, establishing it as an essential tool in various fields. \u003C/p>","\u003Cp style=\"text-align:justify;\">This session aims to explore the diverse applications of Bayesian methods across a wide range of domains, highlighting both theoretical advancements and practical implementations. By doing so, we hope to encourage cross-disciplinary insights and drive forward the development of robust, interpretable, and reliable AI systems. This special session aims to provide an interdisciplinary forum that explores the frontiers of Bayesian methods and their integration into the rapidly evolving field of machine learning. We invite researchers and practitioners from both academia and industry to share their innovative work, discuss challenges, and collectively contribute to advancing the role of probabilistic reasoning and learning in the next generation of AI systems.\u003C/p>","2024-12-13T23:44:30.581Z","2024-12-17T00:08:18.204Z","2024-12-17T00:08:18.183Z","425",[1777,1785,1793],{"id":1778,"name":1779,"committee":16,"position":16,"affiliation":1780,"email":16,"biography":16,"createdAt":1781,"updatedAt":1781,"url_path_id":1782,"contactPhoto":16,"socialLinks":1783,"url_path":1784},293,"Francesco Palmieri","Universita della Campania Luigi Vanvitelli","2024-12-13T23:37:40.362Z","344",[],"-140",{"id":1786,"name":1787,"committee":16,"position":16,"affiliation":1788,"email":16,"biography":16,"createdAt":1789,"updatedAt":1789,"url_path_id":1790,"contactPhoto":16,"socialLinks":1791,"url_path":1792},302,"Giovanni Di Gennaro","Università della Campania Luigi Vanvitelli","2024-12-13T23:37:43.576Z","353",[],"-149",{"id":1794,"name":1795,"committee":16,"position":16,"affiliation":1796,"email":16,"biography":16,"createdAt":1797,"updatedAt":1797,"url_path_id":1798,"contactPhoto":16,"socialLinks":1799,"url_path":1800},235,"Amedeo Buonanno","ENEA","2024-12-13T23:37:22.316Z","286",[],"-82","-221",{"id":799,"session":1803},{"id":272,"title":1804,"teaser":1805,"body":1806,"createdAt":1807,"updatedAt":1808,"publishedAt":1809,"url_path_id":1810,"contacts":1811,"url_path":1843},"Bayesian Neural Networks: The Interplay between Bayes’ Theorem and Neural Networks","\u003Cp style=\"text-align:justify;\">Prof. Zoubin Ghahramani said in his Nature paper, “\u003Ci>intelligence relies on understanding and acting in an imperfectly sensed and uncertain world\u003C/i>”. \u003Cbr>\u003Cbr>Such uncertainty handling ability is even more critical for some safety-critical tasks (e.g., autonomous driving and medical diagnosis). Unfortunately, existing neural networks are weak on that. The topic of this session - Bayesian neural networks - is to combine the beauties of two fields: neural networks which is powerful on complex function approximation and hidden representation learning, and Bayesian which has solid theoretical foundation on uncertainty modeling. \u003C/p>","\u003Cp style=\"text-align:justify;\">It is a newly emerging topic for neural networks. Compared to vanilla neural networks, Bayesian neural networks have distinctive advantages\u003Cbr>\u003Cbr>1) representing, manipulating, and mitigating uncertainty based on the solid theoretical foundations of probability; \u003Cbr>2) encoding the prior knowledge about a problem; and \u003Cbr>3) good interpretability thanks to its clear and meaningful probabilistic structure. \u003C/p>\u003Cp style=\"text-align:justify;\">This area started roughly in 1990s when Radford Neal, David MacKay, and Dayan et al. firstly use Bayesian techniques in neural networks. However, there is not much works following them. As the quick development of both neural networks and Bayesian learning over the past few years, this area has received great interest from the community again, and then many seminal works emerged to lay the theoretical foundation and achieve state-of-the-art performances, such as Dropout as a Bayesian approximation, the connection between Gaussian Process with neural network, Bayesian convolutional neural networks, etc. To keep and enhance such great success, this special session will study the new theories, models, inference algorithms, and applications of this area, and will be a platform to host the recent flourish of ideas using Bayesian approaches in neural networks and using neural networks in Bayesian modelling. Bayesian Neural Networks (BNNs) are highly relevant to IJCNN due to their significant contributions to advancing the field. BNNs enhance the robustness and reliability of neural network models by incorporating uncertainty estimation, which is crucial for applications requiring high confidence in predictions, such as healthcare and autonomous systems. \u003C/p>\u003Cp style=\"text-align:justify;\">They also address overfitting issues by integrating prior distributions over parameters, making them particularly valuable for small or noisy datasets. Furthermore, BNNs improve the calibration of predictive probabilities, ensuring that the predicted outcomes align more closely with actual probabilities. Despite their computational complexity, ongoing advancements in high-performance computing are making BNNs more accessible. Their ability to provide more data-efficient and reliable models makes them a critical topic of discussion and research at neural network conferences, driving innovation and practical applications in the field.\u003C/p>","2024-12-13T23:44:31.245Z","2024-12-17T22:45:56.638Z","2024-12-17T22:45:56.631Z","426",[1812,1819,1827,1835],{"id":1813,"name":1814,"committee":16,"position":16,"affiliation":1349,"email":16,"biography":16,"createdAt":1815,"updatedAt":1815,"url_path_id":1816,"contactPhoto":16,"socialLinks":1817,"url_path":1818},333,"Junyu Xuan","2024-12-13T23:37:57.228Z","384",[],"-180",{"id":1820,"name":1821,"committee":16,"position":16,"affiliation":1822,"email":16,"biography":63,"createdAt":1823,"updatedAt":1823,"url_path_id":1824,"contactPhoto":16,"socialLinks":1825,"url_path":1826},384,"Yuguang Wang","Shanghai Jiao Tong University","2024-12-17T22:44:56.564Z","503",[],"-298",{"id":1828,"name":1829,"committee":16,"position":16,"affiliation":1830,"email":16,"biography":63,"createdAt":1831,"updatedAt":1831,"url_path_id":1832,"contactPhoto":16,"socialLinks":1833,"url_path":1834},385,"Xuhui Fan","Macquarie University","2024-12-17T22:45:13.177Z","504",[],"-299",{"id":1836,"name":1837,"committee":16,"position":16,"affiliation":1838,"email":16,"biography":16,"createdAt":1839,"updatedAt":1839,"url_path_id":1840,"contactPhoto":16,"socialLinks":1841,"url_path":1842},354,"Maoying Qiao","UTS","2024-12-13T23:38:08.858Z","405",[],"-201","-222",{"id":111,"session":1845},{"id":521,"title":1846,"teaser":1847,"body":1848,"createdAt":1849,"updatedAt":1850,"publishedAt":1851,"url_path_id":1852,"contacts":1853,"url_path":1886},"Biologically Inspired Neural Networks and Learning Systems for Robotics and Mechatronics","\u003Cp style=\"text-align:justify;\">The aim of this special session is to bring together research that advances the integration of biologically inspired neural networks and learning systems for robotics and mechatronics. Biologically inspired neural models, such as neural dynamics, have shown promising applications in solving complex problems in robotics, including motion planning, localization, navigation, and mapping. \u003C/p>","\u003Cp style=\"text-align:justify;\">Biologically inspired intelligence represents a crucial and expanding field within computational intelligence, significantly advancing robotics and autonomous systems. The rapid growth in the autonomous robot and mechatronics industries has profoundly impacted both the economy and society, a trend poised to accelerate with the integration of biologically inspired intelligence techniques. These approaches, such as biologically inspired neural networks and learning systems (BNNLS), leverage insights from nature to solve complex challenges in real-world robotics, and mechatronics and autonomous systems. \u003C/p>\u003Cp style=\"text-align:justify;\">By mimicking natural processes and neural architecture, these models enhance robotic functionality and adaptability in dynamic environments. In mechatronic systems, bio-inspired neural networks and learning systems play a critical role in optimizing sensor configuration, improving robot design, advancing motion control, and enabling autonomous system capabilities. Recent advancements in bio-inspired systems for robotics and mechatronics have spurred international research efforts focused on creating adaptive, efficient, and intelligent systems. Key areas include biologically inspired neural network algorithms, brain-inspired neural networks, and emerging deep learning models like deep reinforcement learning, which facilitate complex decision-making and autonomous adaptation. Additionally, swarm intelligence techniques such as swarm intelligence-based neural networks, socially guided neural learning, when fused with BNNLS, yield innovative solutions for cooperative tasks, navigation, and dynamic problem-solving in robotics. This session seeks papers that contribute novel models and methodologies for applying bio-inspired neural approaches to robotics and mechatronics, focusing on both theoretical advancements and practical applications. \u003C/p>\u003Cp style=\"text-align:justify;\">The goal is to highlight the interdisciplinary potential of these approaches in creating efficient, adaptable, and robust systems, fostering discussions on current challenges, emerging trends, and future directions in this field. This special session highlights and promotes the growing interest in emerging research, development, and applications within the dynamic fields of biologically inspired neural networks and learning systems. The session will focus on innovative algorithms and approaches for enhancing robotics, mechatronics, and autonomous systems (such as autonomous robots, unmanned underwater vehicles, and unmanned aerial vehicles), and mechatronics. Further integration of BNNLS with biologically inspired evolutionary algorithms enables advancements across essential applications, including machine vision, pattern recognition, motion control, and sensor-motor coordination. These developments extend to crucial functions such as autonomous motion planning, movement control, and learning in adaptive, time-sensitive environments. As biologically inspired intelligence and learning systems continue to evolve, they promise to enhance the sophistication and functionality of robotic, mechatronics, and vehicle systems, shaping the future of autonomous technologies. Original research papers are invited in the areas of biologically inspired neural networks and learning systems (BNNLS) for robotics and mechatronics. Submissions to this Special Session should emphasize theoretical advancements or innovative applications of biologically inspired computational intelligence algorithms in robotics and mechatronics. Topics may include the theory, design, and application of neural networks and brain-like learning systems in robotics, autonomous systems, and mechatronic applications.\u003C/p>","2024-12-13T23:44:31.820Z","2024-12-17T22:40:05.743Z","2024-12-17T22:40:05.737Z","427",[1854,1862,1870,1878],{"id":1855,"name":1856,"committee":16,"position":16,"affiliation":1857,"email":16,"biography":63,"createdAt":1858,"updatedAt":1858,"url_path_id":1859,"contactPhoto":16,"socialLinks":1860,"url_path":1861},382,"Tingjun Lei","University of North Dakota","2024-12-17T22:39:22.629Z","501",[],"-296",{"id":1863,"name":1864,"committee":16,"position":16,"affiliation":1865,"email":16,"biography":16,"createdAt":1866,"updatedAt":1866,"url_path_id":1867,"contactPhoto":16,"socialLinks":1868,"url_path":1869},254,"Chaomin Luo","Mississippi State University","2024-12-13T23:37:27.888Z","305",[],"-101",{"id":1871,"name":1872,"committee":16,"position":16,"affiliation":1873,"email":16,"biography":16,"createdAt":1874,"updatedAt":1874,"url_path_id":1875,"contactPhoto":16,"socialLinks":1876,"url_path":1877},278,"Erfu Yang","University of Strathclyde","2024-12-13T23:37:35.336Z","329",[],"-125",{"id":1879,"name":1880,"committee":16,"position":16,"affiliation":1881,"email":16,"biography":63,"createdAt":1882,"updatedAt":1882,"url_path_id":1883,"contactPhoto":16,"socialLinks":1884,"url_path":1885},383,"Zhuming Bi","Purdue University Fort Wayne","2024-12-17T22:39:40.195Z","502",[],"-297","-223",{"id":272,"session":1888},{"id":135,"title":1889,"teaser":1890,"body":1891,"createdAt":1892,"updatedAt":1893,"publishedAt":1894,"url_path_id":1895,"contacts":1896,"url_path":1928},"Collaborative Learning of Trustworthy Computational Intelligence Systems (CLOTHES 2025)","\u003Cp style=\"text-align:justify;\">In an era dominated by data-driven insights, designing and building trustworthy Computational Intelligence (CI) systems presents fundamental challenges, especially when leveraging data from decentralized sources. Privacy regulations and ethical concerns have raised the demand for CI systems that are both collaborative and reliable, all while upholding stringent standards of data privacy and transparency. \u003C/p>","\u003Cp style=\"text-align:justify;\">Federated Learning (FL) has emerged as a groundbreaking solution to address these challenges. By allowing multiple parties—such as institutions, corporations, or devices—to collaboratively train models without directly sharing their data, FL provides a paradigm shift that enables decentralized learning while preserving data privacy. \u003C/p>\u003Cp style=\"text-align:justify;\">This approach minimizes the risk of exposing sensitive information and aligns well with evolving regulatory frameworks, such as the GDPR in Europe, which prioritizes data sovereignty. However, to truly achieve trustworthiness in CI, ensuring privacy is only one piece of the puzzle. Explainability and transparency are equally critical, as they allow end-users and stakeholders to understand and trust the decisions made by these systems. The need for model interpretability becomes particularly complex in a Federated Learning setting, where data resides on diverse, decentralized nodes. \u003C/p>\u003Cp style=\"text-align:justify;\">Typically, explainability is achieved either by designing inherently interpretable models or through post-hoc interpretability techniques that elucidate model behavior after training. Yet, when these techniques are applied in the FL context, maintaining both privacy and interpretability poses significant technical and ethical challenges. The aim of this special session is to provide a multidisciplinary and international forum to discuss emerging methodologies for the collaborative learning of CI systems that are both private and trustworthy. This session seeks to explore advanced FL techniques that incorporate robust privacy measures alongside mechanisms for explainability, with the overarching goal of fostering CI models that users and stakeholders can trust. Attendees from various fields—such as machine learning, ethics, law, and policy—are invited to contribute perspectives and solutions that address the unique challenges of building decentralized, privacy-preserving, and interpretable CI systems. This session is motivated by the increasing need to align CI model development with societal expectations for ethical AI, ensuring that systems not only perform effectively but also respect user privacy and maintain transparency. As CI systems are deployed in high-stakes domains such as healthcare, finance, and public policy, trustworthiness is paramount. The specific objectives of this session are threefold: i) To explore and discuss FL approaches that improve model accuracy and robustness while embedding privacy by design. ii) To tackle the challenge of achieving interpretability within the FL framework, ensuring that stakeholders can trust model outputs without compromising sensitive information. iii) To bring together a multidisciplinary community, fostering collaboration across technical, ethical, and legal fields to establish guidelines and best practices for trustworthy CI systems.\u003C/p>","2024-12-13T23:44:32.386Z","2025-01-27T19:50:33.232Z","2024-12-17T23:14:38.293Z","428",[1897,1905,1913,1921],{"id":1898,"name":1899,"committee":16,"position":16,"affiliation":1900,"email":16,"biography":63,"createdAt":1901,"updatedAt":1901,"url_path_id":1902,"contactPhoto":16,"socialLinks":1903,"url_path":1904},386,"Pietro Ducange","University of Pisa","2024-12-17T23:14:32.837Z","505",[],"-300",{"id":1906,"name":1907,"committee":16,"position":16,"affiliation":1908,"email":16,"biography":63,"createdAt":1909,"updatedAt":1909,"url_path_id":1910,"contactPhoto":16,"socialLinks":1911,"url_path":1912},542,"Michela Fazzolari","Istituto di Informatica e Telematica, CNR, Italy","2025-01-27T19:49:28.141Z","702",[],"-494",{"id":1914,"name":1915,"committee":16,"position":16,"affiliation":1916,"email":16,"biography":63,"createdAt":1917,"updatedAt":1917,"url_path_id":1918,"contactPhoto":16,"socialLinks":1919,"url_path":1920},540,"Francesco Marcelloni","University of Pisa, Italy","2025-01-27T19:47:07.666Z","700",[],"-492",{"id":1922,"name":1923,"committee":16,"position":16,"affiliation":1916,"email":16,"biography":63,"createdAt":1924,"updatedAt":1924,"url_path_id":1925,"contactPhoto":16,"socialLinks":1926,"url_path":1927},541,"Alessandro Renda","2025-01-27T19:47:19.310Z","701",[],"-493","-224",{"id":521,"session":1930},{"id":117,"title":1931,"teaser":1932,"body":1933,"createdAt":1934,"updatedAt":1935,"publishedAt":1936,"url_path_id":1937,"contacts":1938,"url_path":1978},"Complex- and Hypercomplex-Valued Neural Networks","\u003Cp style=\"text-align:justify;\">Complex-valued and, more generally, hypercomplex-valued neural networks (HVNNs) constitute a rapidly growing research area that has attracted continued interest for the last decade. Besides their natural ability to treat multidimensional data, hypercomplex-valued neural networks can benefit from hypercomplex numbers’ geometric and algebraic properties. \u003C/p>","\u003Cp style=\"text-align:justify;\">For example, complex-valued neural networks are essential for adequately treating phase and the information contained in phase, including the treatment of waveand rotation-related phenomena such as electromagnetism, light waves, quantum waves, and oscillatory phenomena. Quaternion-valued neural networks, which naturally incorporate spacial rotations and have potential applications in three- and four-dimensional data modeling, have been effectively used to process and analyze multivariate images such as color and polarimetric SAR images. \u003C/p>\u003Cp style=\"text-align:justify;\">Despite significant theoretical development and successful applications, many research directions in HVNNs remain in progress. These include formally generalizing the commonly used real-valued network architectures and training algorithms to the hypercomplex-valued case. There are also many exciting applications in pattern recognition and classification, nonlinear filtering, intelligent image processing, brain-computer interfaces, time-series prediction, bioinformatics, and robotics, to list a few. This special session aims to be the proper forum for a systematic and comprehensive exchange of ideas, presenting recent research results and discussing future trends in complex- and hypercomplex-valued neural networks. \u003C/p>\u003Cp style=\"text-align:justify;\">We hope the proposed session will attract potential speakers and researchers interested in joining the community. We also expect this session to benefit and inspire computational intelligence researchers and other specialties that need sophisticated neural network tools.\u003C/p>","2024-12-13T23:44:32.973Z","2024-12-17T23:24:33.887Z","2024-12-17T23:24:33.871Z","429",[1939,1947,1954,1962,1970],{"id":1940,"name":1941,"committee":16,"position":16,"affiliation":1942,"email":16,"biography":63,"createdAt":1943,"updatedAt":1943,"url_path_id":1944,"contactPhoto":16,"socialLinks":1945,"url_path":1946},387,"Marcos Eduardo Valle","Universidade Estadual de Campinas","2024-12-17T23:23:56.904Z","506",[],"-301",{"id":30,"name":1948,"committee":16,"position":16,"affiliation":1949,"email":16,"biography":63,"createdAt":1950,"updatedAt":1950,"url_path_id":1951,"contactPhoto":16,"socialLinks":1952,"url_path":1953},"Sven Buchholz","Technische Hochschule Brandenburg","2024-12-17T23:24:09.540Z","507",[],"-302",{"id":1955,"name":1956,"committee":16,"position":16,"affiliation":1957,"email":16,"biography":16,"createdAt":1958,"updatedAt":1958,"url_path_id":1959,"contactPhoto":16,"socialLinks":1960,"url_path":1961},272,"Eckhard Hitzer","International Christian University","2024-12-13T23:37:33.422Z","323",[],"-119",{"id":1963,"name":1964,"committee":16,"position":16,"affiliation":1965,"email":16,"biography":16,"createdAt":1966,"updatedAt":1966,"url_path_id":1967,"contactPhoto":16,"socialLinks":1968,"url_path":1969},326,"João Papa","São Paulo State University","2024-12-13T23:37:53.951Z","377",[],"-173",{"id":1971,"name":1972,"committee":16,"position":16,"affiliation":1973,"email":16,"biography":16,"createdAt":1974,"updatedAt":1974,"url_path_id":1975,"contactPhoto":16,"socialLinks":1976,"url_path":1977},222,"Akira Hirose","The University of Tokyo","2024-12-13T23:37:18.886Z","273",[],"-69","-225",{"id":135,"session":1980},{"id":253,"title":1981,"teaser":1982,"body":1983,"createdAt":1984,"updatedAt":1985,"publishedAt":1986,"url_path_id":1987,"contacts":1988,"url_path":2011},"Computational Intelligence and Software Engineering","\u003Cp style=\"text-align:justify;\">In recent years, while the field of Software Engineering (SE) has seen the development of innovative methodologies and frameworks, their broader technological transfer has continued at a gradual pace. This slow uptake is primarily due to the unique challenges within SE as compared to more established engineering disciplines. \u003C/p>","\u003Cp style=\"text-align:justify;\">SE is distinctively complex due to its reliance on human-centered factors, such as knowledge, skills, expertise, and social interactions, which are context-dependent, non-mechanical, and driven by semantic understanding. Addressing these challenges requires a nuanced approach that blends technological and social dimensions, making SE particularly suited to advances in artificial intelligence (AI). The emergence of AI presents a transformative opportunity for SE by introducing new pathways to enhance software quality and improve project success rates. AI technologies can empower SE teams by automating repetitive tasks, enabling deep project analytics, providing actionable insights, and supporting decision-making where complex context and information synthesis are essential. \u003C/p>\u003Cp style=\"text-align:justify;\">Key breakthroughs in AI, including natural language processing (NLP), machine learning (ML), and knowledge-based systems, offer substantial potential for tackling classic SE problems, such as bug prediction, software design recommendation, and requirements engineering. Recent advancements in foundational AI models, like transformer-based architectures (e.g., GPT, BERT), and domain-specific language models, are proving to be invaluable in SE applications. These models are enabling more accurate processing of SE artifacts, from codebases to documentation, and enhancing collaboration among team members through automated insights and context-aware recommendations. \u003C/p>\u003Cp style=\"text-align:justify;\">Beyond NLP, other AI methods such as multi-objective optimization, metaheuristic search, and fuzzy logic have shown promise in addressing complex SE challenges, including code refactoring, fault localization, and software project risk assessment. Moreover, emerging approaches in explainable AI (XAI) bring potential to demystify AI-driven recommendations in SE, improving trust and usability for practitioners. The objective of this special session is to foster closer collaboration between SE and AI communities, thereby driving research innovation, improving educational methods, and ultimately advancing industry practices. Through this integration, we aim to address the pressing needs of SE professionals and researchers by creating AI solutions that are interpretable, scalable, and adaptable to a variety of SE contexts.\u003C/p>","2024-12-13T23:44:33.621Z","2024-12-17T23:29:27.042Z","2024-12-17T23:29:27.035Z","430",[1989,1997,2004],{"id":1990,"name":1991,"committee":16,"position":16,"affiliation":1992,"email":16,"biography":63,"createdAt":1993,"updatedAt":1993,"url_path_id":1994,"contactPhoto":16,"socialLinks":1995,"url_path":1996},389,"Pasquale Ardimento","University of Bari Aldo Moro","2024-12-17T23:28:36.795Z","508",[],"-303",{"id":1998,"name":1999,"committee":16,"position":16,"affiliation":1761,"email":16,"biography":63,"createdAt":2000,"updatedAt":2000,"url_path_id":2001,"contactPhoto":16,"socialLinks":2002,"url_path":2003},390,"Mario Luca Bernardi","2024-12-17T23:28:55.623Z","509",[],"-304",{"id":2005,"name":2006,"committee":16,"position":16,"affiliation":1761,"email":16,"biography":63,"createdAt":2007,"updatedAt":2007,"url_path_id":2008,"contactPhoto":16,"socialLinks":2009,"url_path":2010},391,"Muhammad Usman","2024-12-17T23:29:11.495Z","510",[],"-305","-226",{"id":117,"session":2013},{"id":641,"title":2014,"teaser":2015,"body":2016,"createdAt":2017,"updatedAt":2018,"publishedAt":2019,"url_path_id":2020,"contacts":2021,"url_path":2030},"Computational Intelligence in Transactive Energy Management and Smart Energy Network (CITESEN 2025)","\u003Cp style=\"text-align:justify;\">With the increasing penetration of distributed energy resources, such as electric vehicles (EVs), photovoltaics (PVs) and prosumers, it becomes more challenging for the central system to balance the demand and supply in real-time. \u003C/p>","\u003Cp style=\"text-align:justify;\">The rising of emerging technologies in key sectors such as the rapid development of AI technology and uptake of data centres across the world further complicates the problem and situation.  Local energy markets and smart network services are seen as an efficient and promising solution to enable autonomous and decentralised demand and supply balancing at local level to share the burden of whole system balancing without hindering the evolution of emerging technologies. \u003C/p>\u003Cp style=\"text-align:justify;\">As a result, there are greater interests in investigating new market mechanisms and transactive energy management to support local energy trading and balancing, and how these mechanisms may impact on wholesale energy markets and incumbent suppliers, generators and network operators, and how they may support the integration of high volume of renewable energy and demand responses. These new requirements in transactive energy management and energy markets call for advanced machine learning and computational intelligence techniques to find efficient solutions from advanced energy forecasting to distributed and large-scale energy management. \u003C/p>\u003Cp style=\"text-align:justify;\">This timely special session aims to showcase the latest development in advanced applications of machine learning and computational intelligence to smart energy management and smart energy markets especially in key sectors such as in AI infrastructure and manufacturing, contributing to the ultimate objective of achieving a net-zero society. \u003C/p>","2024-12-13T23:44:34.298Z","2024-12-17T23:30:33.113Z","2024-12-17T23:30:33.106Z","431",[2022],{"id":2023,"name":2024,"committee":16,"position":16,"affiliation":2025,"email":16,"biography":16,"createdAt":2026,"updatedAt":2026,"url_path_id":2027,"contactPhoto":16,"socialLinks":2028,"url_path":2029},281,"Fanlin Meng","University of Exeter","2024-12-13T23:37:36.287Z","332",[],"-128","-227",{"id":253,"session":2032},{"id":259,"title":2033,"teaser":2034,"body":2035,"createdAt":2036,"updatedAt":2037,"publishedAt":2038,"url_path_id":2039,"contacts":2040,"url_path":2057},"Cross-Domain Innovations in Neural Network Methods and Applications","\u003Cp style=\"text-align:justify;\">As neural network techniques progress, their uses increasingly transcend disciplinary borders, crafting a fertile ground for innovation. This special session, \"Cross-Domain Innovations in Neural Network Methods and Applications,\" will highlight groundbreaking research utilizing neural networks across various sectors, including healthcare, finance, climate science, and quantum computing. This session aims to facilitate knowledge sharing and inspire new neural network designs to tackle complicated, real-world issues by bringing together experts from different fields. \u003C/p>","\u003Cp style=\"text-align:justify;\">The session is driven by the understanding that progress in one area can often have applicable value in others, underscoring the crucial need for cross-disciplinary collaboration. For example, the precision-focused models in healthcare can provide insights for assessing financial risks, while the real-time processing of data in environmental science might benefit neuromorphic systems. The goal is to establish a collaborative platform where innovations and challenges specific to each domain are shared, promoting the adaptation of neural network solutions across various sectors. In line with IJCNN 2025’s emphasis, this session will delve into fundamental and applied neural network developments, such as efficient networks, interpretable AI, modular architectures, and ethical AI. The discussions will also cover issues like model reliability, explainability, and ethical considerations, particularly as neural networks become essential to critical infrastructures. The session’s uniqueness stems from its cross-disciplinary angle, highlighting the \"cross-pollination\" of ideas, challenging traditional application boundaries, and examining how innovations like quantum neural networks or transformers can inspire new paths in fields such as cognitive modeling or autonomous systems.\u003C/p>","2024-12-13T23:44:34.953Z","2024-12-18T04:02:04.807Z","2024-12-18T04:02:04.801Z","432",[2041,2049],{"id":2042,"name":2043,"committee":16,"position":16,"affiliation":2044,"email":16,"biography":63,"createdAt":2045,"updatedAt":2045,"url_path_id":2046,"contactPhoto":16,"socialLinks":2047,"url_path":2048},392,"Victor Albuquerque","Federal University of Ceará","2024-12-18T04:01:35.239Z","511",[],"-306",{"id":2050,"name":2051,"committee":16,"position":16,"affiliation":2052,"email":16,"biography":63,"createdAt":2053,"updatedAt":2053,"url_path_id":2054,"contactPhoto":16,"socialLinks":2055,"url_path":2056},393,"Senthil Kumar Jagatheesaperumal","Mepco Schlenk Engineering College","2024-12-18T04:01:51.548Z","512",[],"-307","-228",{"id":641,"session":2059},{"id":647,"title":2060,"teaser":2061,"body":2062,"createdAt":2063,"updatedAt":2064,"publishedAt":2065,"url_path_id":2066,"contacts":2067,"url_path":2091},"Cybersecurity in Complex Environments (CCE)","\u003Cp style=\"text-align:justify;\">Internet of Things (IoT) is facilitated by heterogeneous technologies, which contribute to the providing of innovative and intelligent services in large number of application domains. \u003C/p>","\u003Cp style=\"text-align:justify;\">The satisfaction of security and privacy requirements in this scenario, are becoming a main challenge for IoT systems and their developers. Nevertheless, most efforts on IoT security and privacy requirements look at these requirements from a high level view. Hence, important aspects of security and privacy functionalities will be disregarded, causing wrong design decisions. Exploiting data from infrastructure, computers, cyber physical systems, it can be possible to discover useful information from data in order to securize system also from both administrators and end users. Decision makers can make more informative and conscious decisions through this kind of emerging analysis, including what actions need to be performed, and improvement recommendations to policies, guidelines, procedures, tools, and other aspects of the security of processes. In this context deep learning can properly be used to help deal with issues associated with computer security and computer forensics.\u003C/p>","2024-12-13T23:44:35.575Z","2024-12-18T04:23:11.597Z","2024-12-18T04:23:11.591Z","433",[2068,2076,2084],{"id":2069,"name":2070,"committee":16,"position":16,"affiliation":2071,"email":16,"biography":16,"createdAt":2072,"updatedAt":2072,"url_path_id":2073,"contactPhoto":16,"socialLinks":2074,"url_path":2075},292,"Francesco Mercaldo","University of Molise","2024-12-13T23:37:40.014Z","343",[],"-139",{"id":2077,"name":2078,"committee":16,"position":16,"affiliation":2079,"email":16,"biography":16,"createdAt":2080,"updatedAt":2080,"url_path_id":2081,"contactPhoto":16,"socialLinks":2082,"url_path":2083},242,"Antonella Santone","Unimol","2024-12-13T23:37:24.417Z","293",[],"-89",{"id":2085,"name":2086,"committee":16,"position":16,"affiliation":1780,"email":16,"biography":16,"createdAt":2087,"updatedAt":2087,"url_path_id":2088,"contactPhoto":16,"socialLinks":2089,"url_path":2090},288,"Fiammetta Marulli","2024-12-13T23:37:38.665Z","339",[],"-135","-229",{"id":259,"session":2093},{"id":348,"title":2094,"teaser":2095,"body":2096,"createdAt":2097,"updatedAt":2098,"publishedAt":2099,"url_path_id":2100,"contacts":2101,"url_path":2132},"Data Science: Multidisciplinary Perspectives to Tame the Data Revolution","\u003Cp style=\"text-align:justify;\">The digital transformation is inextricably influencing our lives today. The constant flow of data and technological innovations have reshaped the way we live. The advent of technologies such as cloud computing, the Internet of Things, and Artificial Intelligence (AI) has given rise to an interconnected digital ecosystem, where billions of devices generate an enormous amount of data and information. \u003C/p>","\u003Cp style=\"text-align:justify;\">This \"data explosion” is much more than a mere technological challenge. It is a true revolution that is profoundly affecting our society. Data Science holds the key to tame this revolution. It allows to make the most of this huge amount of data, creating concrete value out of it while enabling new, smart processes and applications. Through sophisticated algorithms and advanced analysis techniques, data science allows to extract knowledge from this mass of raw data, reveal hidden patterns, predict future trends, and support sound decision-making. \u003C/p>\u003Cp style=\"text-align:justify;\">Data science promises, and is already delivering, unmatched efficiency and efficacy touching every sector of our society, from smart cities that optimize traffic and resource management, to intelligent transportation systems that improve safety and efficiency, to digital healthcare that promises more accurate diagnoses and personalized treatments. In the industrial sector, the analysis of data from production lines optimizes processes, reduces waste, and improves quality. In finance, machine learning algorithms predict market trends, assess credit risk, and prevent fraud. Data science is thus becoming the engine of progress, opening new frontiers and offering innovative solutions to complex problems. However, this data-driven revolution comes with new challenges. \u003C/p>\u003Cp style=\"text-align:justify;\">On the one hand, security and privacy, as well as additional non-functional requirements, must be enforced along the entire datadriven pipeline, from data ingestion to AI model deployment, demanding a rethink of the traditional CIA (Confidentiality, Integrity, Availability) triad. On the other hand, a whole new set of (legal) requirements emerge, starting from the ethical implications of AI, to ensure that data-driven technologies are used responsibly and for the benefit of the society as a whole. In addition, a responsible usage of these technologies also implies the usage of large computing infrastructures in a sober, environment-friendly manner. In a nutshell, the data-driven ecosystem represents an extraordinary opportunity for progress and innovation. This means that a multidisciplinary approach is needed to fully exploit its potential, integrating technological, scientific, and ethical skills. This is the only way to build a future in which data are at the service of humanity, contributing to creating a just, sustainable, and prosperous society.\u003C/p>","2024-12-13T23:44:36.382Z","2024-12-18T04:27:17.830Z","2024-12-18T04:27:17.823Z","434",[2102,2110,2118,2125],{"id":2103,"name":2104,"committee":16,"position":16,"affiliation":2105,"email":16,"biography":63,"createdAt":2106,"updatedAt":2106,"url_path_id":2107,"contactPhoto":16,"socialLinks":2108,"url_path":2109},394,"Nicola Bena","Università degli Studi di Milano","2024-12-18T04:27:06.968Z","513",[],"-308",{"id":2111,"name":2112,"committee":16,"position":16,"affiliation":2113,"email":16,"biography":16,"createdAt":2114,"updatedAt":2114,"url_path_id":2115,"contactPhoto":16,"socialLinks":2116,"url_path":2117},274,"Emanuel Di Nardo","University of Naples Parthenope","2024-12-13T23:37:34.049Z","325",[],"-121",{"id":2119,"name":2120,"committee":16,"position":16,"affiliation":2113,"email":16,"biography":16,"createdAt":2121,"updatedAt":2121,"url_path_id":2122,"contactPhoto":16,"socialLinks":2123,"url_path":2124},239,"Angelo Ciaramella","2024-12-13T23:37:23.550Z","290",[],"-86",{"id":2126,"name":2127,"committee":16,"position":16,"affiliation":2105,"email":16,"biography":16,"createdAt":2128,"updatedAt":2128,"url_path_id":2129,"contactPhoto":16,"socialLinks":2130,"url_path":2131},259,"Claudio A. Ardagna","2024-12-13T23:37:29.360Z","310",[],"-106","-230",{"id":647,"session":2134},{"id":390,"title":2135,"teaser":2136,"body":2137,"createdAt":2138,"updatedAt":2139,"publishedAt":2140,"url_path_id":2141,"contacts":2142,"url_path":2174},"Data-Efficient Vision Transformers: Challenges & Applications","\u003Cp style=\"text-align:justify;\">Vision Transformers (ViTs) have revolutionised computer vision, offering state-of-the-art performance across a range of tasks. However, their heavy dependence on large datasets poses significant challenges, particularly in scenarios where data collection is constrained due to cost, privacy, or resource limitations. \u003C/p>","\u003Cp style=\"text-align:justify;\">This special session on Data-efficient Vision Transformers: Challenges & Applications addresses a critical gap by exploring innovative methods to make ViTs viable in data-scarce environments, aligning closely with IJCNN 2025's emphasis on advancing neural networks for real-world applicability. The special session will explore cutting-edge techniques such as self-supervised learning, hybrid models, and generative augmentation strategies to reduce data reliance. \u003C/p>\u003Cp style=\"text-align:justify;\">By bringing together researchers and practitioners, it aims to foster discussions on creating lightweight, efficient ViT architectures optimised for diverse domains, including healthcare, autonomous systems, and smart cities. Furthermore, the focus on practical applications highlights the real-world relevance of these advancements, ensuring the outcomes of this session resonate beyond academia. Incorporating contributions from leading experts in AI and vision transformers, this special session uniquely emphasises the intersection of technical innovation and practical deployment. \u003C/p>\u003Cp style=\"text-align:justify;\">The novel combination of self-supervised approaches, generative modelling, and data-efficient model design ensures its potential to drive impactful solutions for critical sectors. By addressing both foundational challenges and emerging applications, the session promises to push the boundaries of current research, offering transformative insights for participants.\u003C/p>","2024-12-13T23:44:37.336Z","2024-12-18T04:52:27.903Z","2024-12-18T04:52:27.896Z","435",[2143,2151,2159,2167],{"id":2144,"name":2145,"committee":16,"position":16,"affiliation":2146,"email":16,"biography":16,"createdAt":2147,"updatedAt":2147,"url_path_id":2148,"contactPhoto":16,"socialLinks":2149,"url_path":2150},309,"Haider Raza","School of Computer Science and Electronics Engineering, University of Essex","2024-12-13T23:37:46.428Z","360",[],"-156",{"id":2152,"name":2153,"committee":16,"position":16,"affiliation":2154,"email":16,"biography":16,"createdAt":2155,"updatedAt":2155,"url_path_id":2156,"contactPhoto":16,"socialLinks":2157,"url_path":2158},327,"John Q Gan","University of Essex","2024-12-13T23:37:54.421Z","378",[],"-174",{"id":2160,"name":2161,"committee":16,"position":16,"affiliation":2162,"email":16,"biography":63,"createdAt":2163,"updatedAt":2163,"url_path_id":2164,"contactPhoto":16,"socialLinks":2165,"url_path":2166},395,"Muhammad Haris Khan","Mohamed bin Zayed University of Artificial Intelligence","2024-12-18T04:51:53.401Z","514",[],"-309",{"id":2168,"name":2169,"committee":16,"position":16,"affiliation":2154,"email":16,"biography":63,"createdAt":2170,"updatedAt":2170,"url_path_id":2171,"contactPhoto":16,"socialLinks":2172,"url_path":2173},396,"Mohsin Ali","2024-12-18T04:52:09.607Z","515",[],"-310","-231",{"id":348,"session":2176},{"id":793,"title":2177,"teaser":2178,"body":2179,"createdAt":2180,"updatedAt":2181,"publishedAt":2182,"url_path_id":2183,"contacts":2184,"url_path":2208},"Deep Edge Intelligence","\u003Cp style=\"text-align:justify;\">The goal of this event is to bring researchers in machine learning, AI, distributed systems, and electrical and electronic engineering together from across the globe. With the breakthroughs in Deep Learning (DL), recent years have witnessed the booming of Artificial Intelligence (AI) applications and services. \u003C/p>","\u003Cp style=\"text-align:justify;\">Driven by the rapid advances in mobile computing and the Artificial Intelligence of Things (AIoT), billions of mobile and IoT devices are connected to the Internet, generating zillion bytes of data at the network edge. The ability to add intelligence to interconnected devices is at the forefront of this technological revolution. In this regard, conventional machine learning techniques have rapidly adapted to various applications in multiple domains. However, DL techniques, though having demonstrated unparalleled performance primarily in Computer Vision and Natural Language Processing fields, are often subjected to significant computation and memory costs as well as massive data requirements. This poses a great challenge to empower devices at the network edge with DL capability. \u003C/p>\u003Cp style=\"text-align:justify;\">Accelerated by the remarkable success of DL and IoT technologies, there is an urgent need to push the DL frontier to the network edge to fully unleash the potential values of big data. The emerging Edge Computing (EC) paradigm provides a promising way to enable this, which leverages on distributed computing concepts to push computational loads from the network core to the network edge with the aim to provide faster responses to end users. \u003C/p>\u003Cp style=\"text-align:justify;\">Deep Edge Intelligence (DEI) is a combination of DL, AI, EC and IoT. It enables the development and deployment of DL and AI techniques, based on EC, on edge devices, e.g., IoT devices, where the data are generated, aiming to enable diverse use of AI for every person and every organization at any place. This special session seeks to bring together research that sheds light on the ways in which AI, Deep Learning, IoT, edge and fog computing will mutually shape the future of the next generation of information technology.\u003C/p>","2024-12-13T23:44:38.119Z","2024-12-18T05:03:20.410Z","2024-12-18T05:03:20.402Z","436",[2185,2193,2200],{"id":2186,"name":2187,"committee":16,"position":16,"affiliation":2188,"email":16,"biography":16,"createdAt":2189,"updatedAt":2189,"url_path_id":2190,"contactPhoto":16,"socialLinks":2191,"url_path":2192},308,"Hai Dong","RMIT University","2024-12-13T23:37:45.992Z","359",[],"-155",{"id":1068,"name":2194,"committee":16,"position":16,"affiliation":2195,"email":16,"biography":16,"createdAt":2196,"updatedAt":2196,"url_path_id":2197,"contactPhoto":16,"socialLinks":2198,"url_path":2199},"Amit Trivedi","University of Illinois at Chicago","2024-12-13T23:37:22.590Z","287",[],"-83",{"id":2201,"name":2202,"committee":16,"position":16,"affiliation":2203,"email":16,"biography":16,"createdAt":2204,"updatedAt":2204,"url_path_id":2205,"contactPhoto":16,"socialLinks":2206,"url_path":2207},267,"Di Wu","University of Southern Queensland","2024-12-13T23:37:31.861Z","318",[],"-114","-232",{"id":390,"session":2210},{"id":396,"title":2211,"teaser":2212,"body":2213,"createdAt":2214,"updatedAt":2215,"publishedAt":2216,"url_path_id":2217,"contacts":2218,"url_path":2251},"Deep Learning for Digital Twin Models (DLDTM)","\u003Cp style=\"text-align:justify;\">Digital twin models are recently used in variety of research areas where they help to reduce operation costs and prevent possible malfunctions of real world devices. Deep learning models are constantly growing in new aspects, both theoretical and practical, important for various applications in modern technology and industry. \u003C/p>","\u003Cp style=\"text-align:justify;\">One of the recent trends is development is digital twin operation which combine robustness of machine learning techniques with complex real world phenomena. The main goal of this special session is to promote and advance research activities related to all facets of digital twin development by the use of deep learning. Session organizers welcome high-quality original submissions related to digital twin concepts in combination with deep learning, reinforcement learning, autonomous learning, transfer learning or in hybrid constructions with other Artificial Intelligence solutions of neural networks, fuzzy and rule based systems, in both theoretical and practical aspects, oriented on future generation computing.\u003C/p>","2024-12-13T23:44:38.816Z","2024-12-18T05:04:46.171Z","2024-12-18T05:04:46.166Z","437",[2219,2227,2235,2243],{"id":2220,"name":2221,"committee":16,"position":16,"affiliation":2222,"email":16,"biography":16,"createdAt":2223,"updatedAt":2223,"url_path_id":2224,"contactPhoto":16,"socialLinks":2225,"url_path":2226},355,"Marcin Wozniak","Silesian University of Technology","2024-12-13T23:38:09.513Z","406",[],"-202",{"id":2228,"name":2229,"committee":16,"position":16,"affiliation":2230,"email":16,"biography":16,"createdAt":2231,"updatedAt":2231,"url_path_id":2232,"contactPhoto":16,"socialLinks":2233,"url_path":2234},282,"Fazal Ijaz","Melbourne Institute of Technology","2024-12-13T23:37:36.624Z","333",[],"-129",{"id":2236,"name":2237,"committee":16,"position":16,"affiliation":2238,"email":16,"biography":63,"createdAt":2239,"updatedAt":2239,"url_path_id":2240,"contactPhoto":16,"socialLinks":2241,"url_path":2242},397,"Neal Xiong","Sul Ross State University","2024-12-18T05:04:38.049Z","516",[],"-311",{"id":2244,"name":2245,"committee":16,"position":16,"affiliation":2246,"email":16,"biography":16,"createdAt":2247,"updatedAt":2247,"url_path_id":2248,"contactPhoto":16,"socialLinks":2249,"url_path":2250},318,"Jacek Mańdziuk","Warsaw University of Technology","2024-12-13T23:37:50.422Z","369",[],"-165","-233",{"id":793,"session":2253},{"id":812,"title":2254,"teaser":2255,"body":2256,"createdAt":2257,"updatedAt":2258,"publishedAt":2259,"url_path_id":2260,"contacts":2261,"url_path":2294},"Deep Learning in Computational Biology and Biomedicine: from Biomedical Data to Drug Discovery","\u003Cp style=\"text-align:justify;\">In the last decade, the state-of-the-art has seen rapid advancements in designing and training powerful deep Neural Networks (NNs), especially Convolutional NNs, Graph NNs, Variational Autoencoders, Diffusion Models, Transformers, and Large Language Models (LLMs). Applying these AI models to biomedical data has opened unprecedented opportunities in the field of computational biology, revolutionizing both the traditional drug development paradigm and the way to analyze the huge amount of biomedical data coming from multi-omic approaches, which are needed to unravel the underlying mechanisms of diseases. In particular, drug discovery has become increasingly popular after AlphaFold. Drug discovery is a complex process aimed at identifying molecules that can interact with specific molecular targets to treat diseases. \u003C/p>","\u003Cp style=\"text-align:justify;\">It is costly and time-consuming, often requiring over a decade and more than 2 billion dollars to bring a single medicinal product to the market. The main challenges to be addressed consist of (1) the complexity of biological systems, often requiring a multi-omics approach to be understood, (2) the vastness of the chemical space - the conceptual territory inhabited by all possible drug-like compounds - estimated to be in the order of 1060 molecules, and (3) the iterative trial-and-error process on which experimental techniques rely. Traditional analysis methods often struggle to capture the intricate patterns hidden within these multi-omic data, due to their high dimensionality, heterogeneity, and complex interrelationships. \u003C/p>\u003Cp style=\"text-align:justify;\">Thanks to their ability to learn and model complex representations and relationships, advanced NNs offer a powerful solution to tackle these analyses. In addition, by screening large libraries (e.g., predicting molecular properties, binding affinities, and potential toxicity profiles) with unprecedented accuracy, they lead to the early selection of promising candidates, significantly reducing the number of compounds needing slow and expensive experimental testing. For instance, the use of generative models allows the design of new molecules with desired properties, offering novel compounds that might not have been considered using traditional methods and that could target diseases with limited or no existing treatments. However, the effectiveness of these models heavily relies on how the input data are represented and encoded. \u003C/p>\u003Cp style=\"text-align:justify;\">Thus, novel encoding schemes that can capture the underlying biological mechanisms and relationships are crucial for unlocking the full potential of these advanced architectures. This special session seeks to showcase innovative applications of different NN architectures in analyzing various types of biomedical data, including genomics, transcriptomics, proteomics, and metabolomics data, as well as molecular datasets for drug discovery. Furthermore, to explore novel input representation and encoding techniques that enhance NNs' ability to capture complex biological patterns and relationships; Additionally, discuss the challenges and opportunities associated with applying these advanced techniques in real-world biomedical settings. Thus, this special session at IJCNN 2025 focuses on innovative applications of these advanced architectures for analyzing biomedical and (multi-)omics data. \u003C/p>\u003Cp style=\"text-align:justify;\">Special emphasis is placed on novel input representation and encoding techniques, which can enhance the ability of these models to capture complex biological patterns and relationships. The works presented in this special session could enhance the precision of drug discovery efforts and multi-omics analysis, leading to the development of more effective and personalized therapies. These therapies can better address individual patient needs, reduce adverse effects, and improve overall treatment outcomes. By streamlining the identification of suitable drug candidates, computational approaches ultimately contribute to faster access to new therapies for patients and a greater likelihood of successful treatments.\u003C/p>","2024-12-13T23:44:39.574Z","2024-12-18T05:07:06.617Z","2024-12-18T05:07:06.611Z","438",[2262,2270,2278,2286],{"id":2263,"name":2264,"committee":16,"position":16,"affiliation":2265,"email":16,"biography":63,"createdAt":2266,"updatedAt":2266,"url_path_id":2267,"contactPhoto":16,"socialLinks":2268,"url_path":2269},398,"Silvia Multari","Ca' Foscari University of Venice","2024-12-18T05:06:40.812Z","517",[],"-312",{"id":2271,"name":2272,"committee":16,"position":16,"affiliation":2273,"email":16,"biography":16,"createdAt":2274,"updatedAt":2274,"url_path_id":2275,"contactPhoto":16,"socialLinks":2276,"url_path":2277},262,"Daniele Papetti","Università degli Studi Milano-Bicocca","2024-12-13T23:37:30.350Z","313",[],"-109",{"id":2279,"name":2280,"committee":16,"position":16,"affiliation":2281,"email":16,"biography":16,"createdAt":2282,"updatedAt":2282,"url_path_id":2283,"contactPhoto":16,"socialLinks":2284,"url_path":2285},238,"Andrea Tangherloni","Bocconi University","2024-12-13T23:37:23.250Z","289",[],"-85",{"id":2287,"name":2288,"committee":16,"position":16,"affiliation":2289,"email":16,"biography":63,"createdAt":2290,"updatedAt":2290,"url_path_id":2291,"contactPhoto":16,"socialLinks":2292,"url_path":2293},399,"Simone Riva","Oxford University","2024-12-18T05:06:55.075Z","518",[],"-313","-234",{"id":396,"session":2296},{"id":129,"title":2297,"teaser":2298,"body":2299,"createdAt":2300,"updatedAt":2301,"publishedAt":2302,"url_path_id":2303,"contacts":2304,"url_path":2329},"Deep Neural Architecture Generation for Generative Models and Adversarial Learning for Image/Video/Audio/Text Processing","\u003Cp style=\"text-align:justify;\">Generative Adversarial Networks (GANs) have become new hotspots of Artificial Intelligence. Various GAN-inspired and variant models (e.g. conditional GAN (cGAN), auxiliary classifier GAN (AC-GAN), bidirectional GAN (BiGAN), semi-supervised GAN and variational autoencoder GAN (VAE-GAN)) have been developed for image generation, segmentation, detection and classification, as well as video/audio synthesis/retrieval/restoration/domain adaptation. Such developments have contributed to a variety of applications, such as personalized story-telling, animated movie generation, building/interior design, e-learning, medical diagnosis, surveillance, agriculture, deepfake generation, urban land use detection, and underwater/forest observation using multispectral/hyperspectral images. \u003C/p>","\u003Cp style=\"text-align:justify;\">The design of new and effective variant architectures of GANs has attracted significant attention. In parallel, reinforcement learning and evolutionary algorithms have demonstrated superior performance in automated deep neural architecture generation. As popular reinforcement learning methods, deep Q-learning, Proximal Policy Optimization (PPO), actor-critic and Deep Deterministic Policy Gradient (DDPG) algorithms, have been adopted in various existing studies for optimal network architecture generation and hyper-parameter optimization. \u003C/p>\u003Cp style=\"text-align:justify;\">A variety of recent state-of-the-art swarm intelligence algorithms (e.g. Sparrow Search Algorithm, Tree Search Optimization and Marine Predators Algorithm) and hybrid methods (e.g. evolutionary algorithms combined with reinforcement learning models) have also been developed and deployed in single, multi and many-objective optimization problems for neural architecture search for image, video, sound and text classification problems. This special issue aims to stimulate research and discussion on GAN-inspired methods as well as automatic machine learning methods for GAN architecture generation for a variety of image/video/signal and natural language processing problems. It also aims to stimulate new developments to address gaps such as deep network generation for GANs as well as other hybrid/cascaded architectures with residual/dense connectivity to tackle vanishing gradients for complex image processing tasks such as image description and visual question generation.\u003C/p>","2024-12-13T23:44:40.302Z","2024-12-18T05:08:53.016Z","2024-12-18T05:08:53.011Z","439",[2305,2313,2321],{"id":2306,"name":2307,"committee":16,"position":16,"affiliation":2308,"email":16,"biography":16,"createdAt":2309,"updatedAt":2309,"url_path_id":2310,"contactPhoto":16,"socialLinks":2311,"url_path":2312},343,"Li Zhang","Royal Holloway, University of London","2024-12-13T23:38:02.401Z","394",[],"-190",{"id":2314,"name":2315,"committee":16,"position":16,"affiliation":2316,"email":16,"biography":16,"createdAt":2317,"updatedAt":2317,"url_path_id":2318,"contactPhoto":16,"socialLinks":2319,"url_path":2320},255,"Chee Peng Lim","Swinburne University of Technology","2024-12-13T23:37:28.187Z","306",[],"-102",{"id":2322,"name":2323,"committee":16,"position":16,"affiliation":2324,"email":16,"biography":16,"createdAt":2325,"updatedAt":2325,"url_path_id":2326,"contactPhoto":16,"socialLinks":2327,"url_path":2328},332,"Jungong Han","University of Sheffield","2024-12-13T23:37:56.764Z","383",[],"-179","-235",{"id":812,"session":2331},{"id":234,"title":2332,"teaser":2333,"body":2334,"createdAt":2335,"updatedAt":2336,"publishedAt":2337,"url_path_id":2338,"contacts":2339,"url_path":2363},"Deep Vision in Space","\u003Cp style=\"text-align:justify;\">Modern AI and advanced sensing technologies have been transforming our ability to observe the Earth and explore the Universe as well as monitor space objects. By analysing and interpreting multifaceted data (primarily imagery) captured by sensing devices on aircrafts, UAVs, satellites, spacecrafts, and astronomical telescopes that operate either on ground or in orbit, insights can be gained to enable intelligent decision-making with high autonomy. \u003C/p>","\u003Cp style=\"text-align:justify;\">Recent years have witnessed rapid advances in remote sensing technologies, resulting in an explosive growth of Earth observation data for probing the entire Earth at daily or even finer granularity. Meanwhile, many new astronomical telescopes with enhanced sensing capabilities, like the recently launched James Webb Space Telescope, have been put into operation, generating massive data about the never explored aspects of the Universe. Also, space domain awareness has become a trending topic for intelligent surveillance and coordination of various space objects. \u003C/p>\u003Cp style=\"text-align:justify;\">Nowadays, thanks to the boom of modern AI techniques, particularly deep learning, armed by an unprecedented growth in super-computing power and on-board computing capability, such space data can be transformed into valuable scientific discoveries and actionable insights which may benefit various fields, such as astronomy, transportation, agriculture, and environment. However, the rapidly increasing complexity and requirements of newly emerging applications in different fields are posing greater challenges to existing AI techniques, leading to the surging needs of technology advancement. \u003C/p>\u003Cp style=\"text-align:justify;\">This special session aims to bring together researchers from academia, governments and industries to review past achievements, disseminate latest studies, and explore future directions about innovating and applying modern AI techniques, particularly deep learning (the key theme of IJCNN), to analyse space data, e.g., remote sensing and astronomical imagery, with the aim of fully unleashing the potential values of space data to benefit wider‐ranging fields.\u003C/p>","2024-12-13T23:44:40.994Z","2024-12-18T05:10:52.379Z","2024-12-18T05:10:52.374Z","440",[2340,2347,2355],{"id":2341,"name":2342,"committee":16,"position":16,"affiliation":2316,"email":16,"biography":16,"createdAt":2343,"updatedAt":2343,"url_path_id":2344,"contactPhoto":16,"socialLinks":2345,"url_path":2346},220,"A. K. Qin","2024-12-13T23:37:18.186Z","271",[],"-67",{"id":2348,"name":2349,"committee":16,"position":16,"affiliation":2350,"email":16,"biography":63,"createdAt":2351,"updatedAt":2351,"url_path_id":2352,"contactPhoto":16,"socialLinks":2353,"url_path":2354},400,"Plamen Angelov","Lancaster University","2024-12-18T05:10:23.341Z","519",[],"-314",{"id":2356,"name":2357,"committee":16,"position":16,"affiliation":2358,"email":16,"biography":63,"createdAt":2359,"updatedAt":2359,"url_path_id":2360,"contactPhoto":16,"socialLinks":2361,"url_path":2362},401,"Yuan-Sen Ting","The Ohio State University","2024-12-18T05:10:41.650Z","520",[],"-315","-236",{"id":129,"session":2365},{"id":317,"title":2366,"teaser":2367,"body":2368,"createdAt":2369,"updatedAt":2370,"publishedAt":2371,"url_path_id":2372,"contacts":2373,"url_path":2442},"Design and Theory of Deep Graph Learning","\u003Cp style=\"text-align:justify;\">Graph structures allow to represent structured/complex data with entities and their relationships. These data structures naturally characterize a wide range of problems, including the areas of bio/chemistry (e.g. (macro-)molecules, proteins, biological networks), natural language processing (e.g. strings and parse trees), social network analysis (e.g. link prediction, object identification), information dissemination on social networks (temporal/dynamics graphs), and epidemiological studies (graph agent-based models). \u003C/p>","\u003Cp style=\"text-align:justify;\">In general, graphs offer an extremely flexible tool to describe directly and effectively the relationships between data items that can be lost by the “flat” (vector) representations used by traditional Machine Learning (ML) and Neural Networks (NNs) tools. The extension of ML/NNs to graph domains makes it possible to address, in a systematic and general way, this variety of problems with data-driven approaches. By being able to deal with the inherent nature of structured data, learning models are endowed with a formidable capability and flexibility to address new domains and to improve accuracy and efficiency in solving complex problems. However, there are still many open points and challenges for basic and applied research, as the research in ML/NNs for graphs generalizes in a non-obvious way theoretical and modeling issues already mature in vector domains. \u003C/p>\u003Cp style=\"text-align:justify;\">This special session aims to bring together cutting-edge research and new ideas in deep learning for graphs, addressing open challenges and advancing both theoretical and practical perspectives. Despite rapid progress, this field continues to present unique challenges—such as model generalization, structure learning, and the adaptation of methods developed for vector spaces to graph domains. The community's interest in graph-based ML/NNs has grown significantly, as seen in major conferences: NeurIPS (169 in 2022; 202 in 2023), ICML (122 in 2023; 140 in 2024), ICLR (77 in 2022; 112 in 2023), and AAAI (202 in 2023; 254 in 2024), consistently representing 5-10% of their respective proceedings. \u003C/p>\u003Cp style=\"text-align:justify;\">IJCNN and WCCI have successfully organized sessions on related topics in recent years, with the 2024 IJCNN special session alone receiving over 43 submissions. Further engagement in this field is evident from similar sessions held by leading conferences such as CVPR, ECML-PKDD, and INNS BDDL. Our proposed special session for IJCNN 2025 seeks to serve as a key gathering for researchers to discuss both foundational developments and innovative applications within the expanding domain of graph-based deep learning. We invite papers that present advances in model design, structure learning, graph kernels, and graph stream processing, alongside theoretical insights, benchmarks, and impactful applications across disciplines. This session offers an exceptional opportunity for researchers to share insights, highlight emerging applications, and set new directions for the future of machine learning on graphs.\u003C/p>","2024-12-13T23:44:41.643Z","2024-12-18T05:14:22.657Z","2024-12-18T05:14:22.651Z","441",[2374,2382,2390,2397,2404,2412,2420,2428,2435],{"id":2375,"name":2376,"committee":16,"position":16,"affiliation":2377,"email":16,"biography":63,"createdAt":2378,"updatedAt":2378,"url_path_id":2379,"contactPhoto":16,"socialLinks":2380,"url_path":2381},402,"Ming Li","Zhejiang Normal University","2024-12-18T05:13:09.354Z","521",[],"-316",{"id":2383,"name":2384,"committee":16,"position":16,"affiliation":2385,"email":16,"biography":63,"createdAt":2386,"updatedAt":2386,"url_path_id":2387,"contactPhoto":16,"socialLinks":2388,"url_path":2389},403,"Pietro Lió","University of Cambridge","2024-12-18T05:13:23.343Z","522",[],"-317",{"id":2391,"name":2392,"committee":16,"position":16,"affiliation":1900,"email":16,"biography":16,"createdAt":2393,"updatedAt":2393,"url_path_id":2394,"contactPhoto":16,"socialLinks":2395,"url_path":2396},231,"Alessio Micheli","2024-12-13T23:37:21.220Z","282",[],"-78",{"id":827,"name":2398,"committee":16,"position":16,"affiliation":2399,"email":16,"biography":63,"createdAt":2400,"updatedAt":2400,"url_path_id":2401,"contactPhoto":16,"socialLinks":2402,"url_path":2403},"Nicolò Navarin","Università di Padova","2024-12-18T05:13:38.758Z","523",[],"-318",{"id":2405,"name":2406,"committee":16,"position":16,"affiliation":2407,"email":16,"biography":16,"createdAt":2408,"updatedAt":2408,"url_path_id":2409,"contactPhoto":16,"socialLinks":2410,"url_path":2411},346,"Luca Pasa","Università Degli Studi di Padova","2024-12-13T23:38:04.462Z","397",[],"-193",{"id":2413,"name":2414,"committee":16,"position":16,"affiliation":2415,"email":16,"biography":16,"createdAt":2416,"updatedAt":2416,"url_path_id":2417,"contactPhoto":16,"socialLinks":2418,"url_path":2419},264,"Davide Rigoni","University of Padova","2024-12-13T23:37:30.941Z","315",[],"-111",{"id":2421,"name":2422,"committee":16,"position":16,"affiliation":2423,"email":16,"biography":16,"createdAt":2424,"updatedAt":2424,"url_path_id":2425,"contactPhoto":16,"socialLinks":2426,"url_path":2427},297,"Franco Scarselli","University of Siena","2024-12-13T23:37:41.770Z","348",[],"-144",{"id":2429,"name":2430,"committee":16,"position":16,"affiliation":2399,"email":16,"biography":16,"createdAt":2431,"updatedAt":2431,"url_path_id":2432,"contactPhoto":16,"socialLinks":2433,"url_path":2434},228,"Alessandro Sperduti","2024-12-13T23:37:20.508Z","279",[],"-75",{"id":2436,"name":2437,"committee":16,"position":16,"affiliation":1900,"email":16,"biography":16,"createdAt":2438,"updatedAt":2438,"url_path_id":2439,"contactPhoto":16,"socialLinks":2440,"url_path":2441},269,"Domenico Tortorella","2024-12-13T23:37:32.454Z","320",[],"-116","-237",{"id":310,"session":2444},{"id":290,"title":2445,"teaser":2446,"body":2447,"createdAt":2448,"updatedAt":2449,"publishedAt":2450,"url_path_id":2451,"contacts":2452,"url_path":2485},"Digital Twinning in Smart Applications","\u003Cp style=\"text-align:justify;\">The advent of digital twins has revolutionized the simulation and optimization of real-world scenarios. Digital twins are comparable virtual replicas of real-world systems, assets, or processes that allow for real-time optimization, simulation, and monitoring. Through a complete or semi-complete digital replication of a physical object, they provide performance analysis, problem prediction, and scenario testing without affecting the real system. \u003C/p>","\u003Cp style=\"text-align:justify;\">When combined with deep learning, these virtual replicas gain the ability to learn from extensive data, adapt to changing conditions, and predict future states with exceptional precision. \u003Cbr>\u003Cbr>This integration enables digital twins to not only reflect their physical counterparts but also anticipate issues, enhance performance, and autonomously support decision-making processes. The applications are extensive: in manufacturing, it leads to smart factories where production lines optimize themselves for efficiency; in healthcare, patient-specific digital twins can forecast health trajectories and tailor treatments; in urban planning, city-wide digital twins can model traffic and energy use to improve sustainability. Deep learning allows digital twins to become dynamic entities that change in tandem with their physical counterparts, creating interesting prospects for innovation in a variety of research and applications areas. \u003Cbr>\u003Cbr>The integration of digital twins with deep learning drives significant advancements in intelligent systems, enabling real-time optimization, predictive capabilities, and autonomous decision-making, core themes in neural network research. This special session aims to gather contributions that provide new insights and innovations in the field of Deep Learning for Digital Twinning. A key goal is to strengthen the community of researchers working in this domain, fostering the generation of innovative ideas to tackle current challenges. The session seeks to create opportunities for collaboration on future projects and initiatives, promoting lasting partnerships among experts in Deep Learning and Digital Twin technologies.\u003C/p>","2024-12-13T23:44:42.316Z","2024-12-24T00:35:39.073Z","2024-12-24T00:35:39.067Z","442",[2453,2461,2469,2477],{"id":2454,"name":2455,"committee":16,"position":16,"affiliation":2456,"email":16,"biography":16,"createdAt":2457,"updatedAt":2457,"url_path_id":2458,"contactPhoto":16,"socialLinks":2459,"url_path":2460},316,"Imad Rida","UTC","2024-12-13T23:37:49.509Z","367",[],"-163",{"id":2462,"name":2463,"committee":16,"position":16,"affiliation":2464,"email":16,"biography":16,"createdAt":2465,"updatedAt":2465,"url_path_id":2466,"contactPhoto":16,"socialLinks":2467,"url_path":2468},252,"Carmen Bisogni","Università degli Studi di Salerno","2024-12-13T23:37:27.293Z","303",[],"-99",{"id":2470,"name":2471,"committee":16,"position":16,"affiliation":2472,"email":16,"biography":16,"createdAt":2473,"updatedAt":2473,"url_path_id":2474,"contactPhoto":16,"socialLinks":2475,"url_path":2476},348,"Lucia Cascone","University of Salerno","2024-12-13T23:38:05.617Z","399",[],"-195",{"id":2478,"name":2479,"committee":16,"position":16,"affiliation":2480,"email":16,"biography":16,"createdAt":2481,"updatedAt":2481,"url_path_id":2482,"contactPhoto":16,"socialLinks":2483,"url_path":2484},284,"Fei Hao","Shaanxi Normal University","2024-12-13T23:37:37.293Z","335",[],"-131","-238",{"id":681,"session":2487},{"id":310,"title":2488,"teaser":2489,"body":2490,"createdAt":2491,"updatedAt":2492,"publishedAt":2493,"url_path_id":2494,"contacts":2495,"url_path":2505},"Distributed Learning and Intelligent Systems: Advancing Privacy and Scalability for IoT and Edge Networks","\u003Cp style=\"text-align:justify;\">The scope of this workshop is to address the growing challenges of using distributed machine learning (ML) and artificial intelligence (AI) in Internet of Things (IoT) devices and edge computing systems. \u003C/p>","\u003Cp style=\"text-align:justify;\">These systems, which are increasingly used in smart cities, industrial automation, healthcare, and other fields, depend on decentralized networks to process data and make realtime decisions on devices with limited computational power. The workshop focuses on three key themes: scalability, privacy, and efficiency. It aims to explore solutions that enhance the scalability of distributed learning systems across large IoT ecosystems, protect user data through privacypreserving methods, and ensure that intelligent systems can operate efficiently on resourceconstrained edge devices.\u003C/p>","2024-12-13T23:44:42.964Z","2024-12-24T00:37:33.149Z","2024-12-24T00:37:33.141Z","443",[2496],{"id":2497,"name":2498,"committee":16,"position":16,"affiliation":2499,"email":16,"biography":63,"createdAt":2500,"updatedAt":2501,"url_path_id":2502,"contactPhoto":16,"socialLinks":2503,"url_path":2504},407,"Wadii Boulila","Prince Sultan University","2024-12-24T00:37:20.099Z","2024-12-24T00:37:24.663Z","528",[],"-323","-239",{"id":182,"session":2507},{"id":681,"title":2508,"teaser":2509,"body":2510,"createdAt":2511,"updatedAt":2512,"publishedAt":2513,"url_path_id":2514,"contacts":2515,"url_path":2561},"Domain Adaptation for Complex Situations: Theories, Algorithms and Applications","\u003Cp style=\"text-align:justify;\">Transfer learning aims to leverage knowledge acquired from source models to tackle target tasks, even when the source and target data come from different distributions or modalities. \u003C/p>","\u003Cp style=\"text-align:justify;\">In recent years, foundational models and multimodal approaches have prospered in transfer learning, with substantial evidence of successful investigations into both the theoretical development and applications in various real-world contexts, including primarily computer vision, as well as fields such as natural language processing, privacy protection, generative AI, autonomous systems, robotics and healthcare. Offering a unified perspective on current trends in both fundamental and applied research on transfer learning is essential for advancing artificial intelligence, generative models, and practical decision support systems. This special session aims to provide a forum for researchers working in transfer learning across modalities to share the latest advancements in theories, algorithms, models, and applications.\u003C/p>","2024-12-13T23:44:43.675Z","2024-12-24T00:46:33.285Z","2024-12-24T00:46:33.280Z","444",[2516,2524,2532,2539,2547,2554],{"id":2517,"name":2518,"committee":16,"position":16,"affiliation":2519,"email":16,"biography":16,"createdAt":2520,"updatedAt":2520,"url_path_id":2521,"contactPhoto":16,"socialLinks":2522,"url_path":2523},337,"Keqiuyin Li","University of Technology Syndey","2024-12-13T23:37:59.030Z","388",[],"-184",{"id":2525,"name":2526,"committee":16,"position":16,"affiliation":1349,"email":16,"biography":63,"createdAt":2527,"updatedAt":2528,"url_path_id":2529,"contactPhoto":16,"socialLinks":2530,"url_path":2531},408,"Zhen Fang","2024-12-24T00:46:11.606Z","2024-12-24T00:46:20.167Z","529",[],"-324",{"id":2533,"name":2534,"committee":16,"position":16,"affiliation":1349,"email":16,"biography":16,"createdAt":2535,"updatedAt":2535,"url_path_id":2536,"contactPhoto":16,"socialLinks":2537,"url_path":2538},315,"Hua Zuo","2024-12-13T23:37:49.075Z","366",[],"-162",{"id":2540,"name":2541,"committee":16,"position":16,"affiliation":2542,"email":16,"biography":16,"createdAt":2543,"updatedAt":2543,"url_path_id":2544,"contactPhoto":16,"socialLinks":2545,"url_path":2546},349,"Luis Martinez","University of Jaén","2024-12-13T23:38:06.192Z","400",[],"-196",{"id":2548,"name":2549,"committee":16,"position":16,"affiliation":1349,"email":16,"biography":16,"createdAt":2550,"updatedAt":2550,"url_path_id":2551,"contactPhoto":16,"socialLinks":2552,"url_path":2553},305,"Guangquan Zhang","2024-12-13T23:37:44.763Z","356",[],"-152",{"id":2555,"name":2556,"committee":16,"position":16,"affiliation":1349,"email":16,"biography":16,"createdAt":2557,"updatedAt":2557,"url_path_id":2558,"contactPhoto":16,"socialLinks":2559,"url_path":2560},322,"Jie Lu","2024-12-13T23:37:52.145Z","373",[],"-169","-240",{"id":39,"session":2563},{"id":182,"title":2564,"teaser":2565,"body":2566,"createdAt":2567,"updatedAt":2568,"publishedAt":2569,"url_path_id":2570,"contacts":2571,"url_path":2604},"Ethical, Legal and Social Implications of Computational Intelligence","\u003Cp style=\"text-align:justify;\">A recurring concern in the use of neural network-based models is the opaqueness/lack of transparency and explainability as well as risk assessment. With the rise of generative AI and foundational models, specifically large language models and vision transformers, we need to ensure that our computational scientists are integrating AI ethics in every component and addressing security and privacy issues. \u003C/p>","\u003Cp style=\"text-align:justify;\">This emphasizes the need for intentional ethics-based approaches that address all facets of AI/Computational Intelligence (CI) to ensure safe and responsible use. From industry to academia, we need to consider how to create the content responsibly and interpretability, in particular in foundational models that will heavily impact our society. We welcome papers that discuss these challenges and propose solutions. This special session welcomes papers on novel technical contributions to the field of AI/CI Ethics (including fairness, explainability, risk, accountability and responsibility) especially as it relates to neural network-based applications. \u003C/p>\u003Cp style=\"text-align:justify;\">We will also consider novel research in the field of data-driven guidelines and recommendations on responsible AI policies, standards, and methodologies; social science studies and recommendations related to the impact of AI on society, as well as surveys of the state-of-the-art in the space of AI ethics. Novel interdisciplinary research and industry submissions are welcome. Objectives: To discuss the ethical and moral principles that govern the behavior of AI/CI technology, as well as the operator, user and stakeholders who are impacted by decisions informed by such technologies. These principles should cover the following: balancing the ecological footprint of technologies against the economic benefits; managing the impact of automation on the workforce; ensuring privacy is not adversely affected; and dealing with the legal implications of embodying AI/CI technologies in autonomous systems. As the largest technical event in the field of neural networks and CI at large, IJCNN provides an ideal forum for discussion of these issues.\u003C/p>","2024-12-13T23:44:44.280Z","2025-04-22T22:52:25.978Z","2024-12-24T00:48:17.574Z","445",[2572,2580,2588,2596],{"id":2573,"name":2574,"committee":16,"position":16,"affiliation":2575,"email":16,"biography":63,"createdAt":2576,"updatedAt":2576,"url_path_id":2577,"contactPhoto":16,"socialLinks":2578,"url_path":2579},409,"Tayo Obafemi-Ajayi","Missouri State University","2024-12-24T00:48:07.991Z","530",[],"-325",{"id":2581,"name":2582,"committee":16,"position":16,"affiliation":2583,"email":16,"biography":63,"createdAt":2584,"updatedAt":2584,"url_path_id":2585,"contactPhoto":16,"socialLinks":2586,"url_path":2587},559,"Hava Siegelmann","University of Massachusetts, Amherst, USA","2025-04-22T22:51:31.051Z","724",[],"-513",{"id":2589,"name":2590,"committee":16,"position":16,"affiliation":2591,"email":16,"biography":63,"createdAt":2592,"updatedAt":2592,"url_path_id":2593,"contactPhoto":16,"socialLinks":2594,"url_path":2595},560,"Catherine Huang","Google Inc., USA","2025-04-22T22:51:46.894Z","725",[],"-514",{"id":2597,"name":2598,"committee":16,"position":16,"affiliation":2599,"email":16,"biography":63,"createdAt":2600,"updatedAt":2600,"url_path_id":2601,"contactPhoto":16,"socialLinks":2602,"url_path":2603},561,"John Sheppard ","Montana State University, USA","2025-04-22T22:52:01.558Z","726",[],"-515","-241",{"id":176,"session":2606},{"id":39,"title":2607,"teaser":2608,"body":2609,"createdAt":2610,"updatedAt":2611,"publishedAt":2612,"url_path_id":2613,"contacts":2614,"url_path":2623},"Evolutionary Computation in Wireless Communications","\u003Cp style=\"text-align:justify;\">Evolutionary computation is a computational paradigm inspired by the principles of biological evolution, and it has found applications in various fields, including wireless communications. Evolutionary algorithms simulate the process of natural selection, reproduction, and mutation to evolve solutions to optimization problems. \u003C/p>","\u003Cp style=\"text-align:justify;\">In the context of wireless communications, evolutionary techniques are employed to optimize and adapt wireless systems to dynamic and complex environments. Wireless communication systems often face optimization challenges, such as resource allocation, power control, and network configuration. Evolutionary computation can optimize the allocation of resources like frequency bands, time slots, and power to maximize network performance and minimize interference. Wireless communication environments are dynamic and subject to changes in user demand, interference, and channel conditions. Evolutionary computation provides adaptive solutions that can continuously evolve and adjust to changing circumstances, making it well-suited for dynamic wireless scenarios. \u003C/p>\u003Cp style=\"text-align:justify;\">Many wireless communication problems involve multiple conflicting objectives, such as maximizing throughput while minimizing power consumption. Evolutionary computation excels in handling multi-objective optimization, offering a set of solutions representing trade-offs between conflicting goals (Pareto front). Research challenges still exist, including the need for efficient algorithms capable of handling real-time optimization, scalability for large-scale networks, and addressing diverse and evolving wireless communication standards. In this special session, we would like to invite worldwide researcher to share and present their latest research progresses on theory, methodology and application about evolutionary computation in wireless communications, including but not limited to evolutionary algorithms, machine learning and deep learning.\u003C/p>","2024-12-13T23:44:44.906Z","2024-12-24T00:50:13.522Z","2024-12-24T00:50:13.517Z","446",[2615],{"id":2616,"name":2617,"committee":16,"position":16,"affiliation":2618,"email":16,"biography":63,"createdAt":2619,"updatedAt":2619,"url_path_id":2620,"contactPhoto":16,"socialLinks":2621,"url_path":2622},410,"Weiwei Jiang","Beijing University of Posts and Telecommunications","2024-12-24T00:50:05.631Z","531",[],"-326","-242",{"id":499,"session":2625},{"id":176,"title":2626,"teaser":2627,"body":2628,"createdAt":2629,"updatedAt":2630,"publishedAt":2631,"url_path_id":2632,"contacts":2633,"url_path":2670},"Explainable AI in Neural Networks: Advances, Challenges, and Applications","\u003Cp style=\"text-align:justify;\">The rise of AI in critical fields such as healthcare, autonomous systems, and finance demands greater transparency in decision-making processes. Neural networks, despite their high performance, remain opaque, creating a barrier to trust and accountability. \u003C/p>","\u003Cp style=\"text-align:justify;\">The European Union’s AI Act and similar regulatory frameworks highlight the need for AI systems to be both explainable and fair. \u003C/p>\u003Cp style=\"text-align:justify;\">This session addresses the dual challenge of enhancing transparency in neural networks while meeting the increasing regulatory and ethical requirements for explainable AI (XAI). The session aims to explore the latest XAI methods that make neural networks more interpretable without sacrificing performance. It will focus on the development of new techniques that meet normative standards, with a particular emphasis on bias mitigation, fairness, and societal impacts. Through an interdisciplinary approach, the session seeks to advance both the technical and regulatory aspects of XAI for neural networks, fostering collaboration between academia, industry, and policymakers. \u003C/p>\u003Cp style=\"text-align:justify;\">This session will introduce innovative approaches such as neuro-symbolic alignment and monosemanticity, where neural network models are broken down into interpretable components, as seen in recent advancements by Anthropic . On the one hand, this new approach can be compared with consolidated XAI techniques such as Shapley values; on the other, this fits perfectly with the DARPA vision of finding and verifying meaningful parts of objects to support the prediction. The session will also emphasize bias detection and fairness, linking XAI techniques to societal and ethical challenges, including regulatory compliance with the AI Act. The focus on the intersection of XAI techniques and societal impacts provides a fresh perspective on how neural networks can be made transparent and trustworthy.\u003C/p>","2024-12-13T23:44:45.577Z","2024-12-24T01:00:14.881Z","2024-12-24T01:00:14.876Z","447",[2634,2642,2650,2652,2660,2662],{"id":2635,"name":2636,"committee":16,"position":16,"affiliation":2637,"email":16,"biography":16,"createdAt":2638,"updatedAt":2638,"url_path_id":2639,"contactPhoto":16,"socialLinks":2640,"url_path":2641},223,"Alan Perotti","CENTAI Institute","2024-12-13T23:37:19.207Z","274",[],"-70",{"id":2643,"name":2644,"committee":16,"position":16,"affiliation":2645,"email":16,"biography":63,"createdAt":2646,"updatedAt":2646,"url_path_id":2647,"contactPhoto":16,"socialLinks":2648,"url_path":2649},411,"Qi Chen","Victoria University of Wellington","2024-12-24T00:59:28.224Z","532",[],"-327",{"id":1438,"name":1439,"committee":16,"position":16,"affiliation":1440,"email":16,"biography":16,"createdAt":1441,"updatedAt":1441,"url_path_id":1442,"contactPhoto":16,"socialLinks":2651,"url_path":1444},[],{"id":2653,"name":2654,"committee":16,"position":16,"affiliation":2655,"email":16,"biography":63,"createdAt":2656,"updatedAt":2656,"url_path_id":2657,"contactPhoto":16,"socialLinks":2658,"url_path":2659},412,"Paulo Lisboa","Liverpool John Moores University","2024-12-24T00:59:44.847Z","533",[],"-328",{"id":1485,"name":1486,"committee":16,"position":16,"affiliation":1487,"email":16,"biography":16,"createdAt":1488,"updatedAt":1488,"url_path_id":1489,"contactPhoto":16,"socialLinks":2661,"url_path":1491},[],{"id":2663,"name":2664,"committee":16,"position":16,"affiliation":2665,"email":16,"biography":16,"createdAt":2666,"updatedAt":2666,"url_path_id":2667,"contactPhoto":16,"socialLinks":2668,"url_path":2669},232,"Alfredo Vellido","Universitat Politecnica de Catalunya","2024-12-13T23:37:21.503Z","283",[],"-79","-243",{"id":433,"session":2672},{"id":499,"title":2673,"teaser":2674,"body":2675,"createdAt":2676,"updatedAt":2677,"publishedAt":2678,"url_path_id":2679,"contacts":2680,"url_path":2695},"Explainable Artificial Intelligence in Bioengineering (EAIB)","\u003Cp style=\"text-align:justify;\">Artificial intelligence is widely adopted in bioinformatics and bioengineering. As a matter of fact when the diagnosis or selection of therapy is no longer performed exclusively by the physician, but to a significant extent by artificial intelligence, decisions easily become nontransparent. The most common application of machine learning algorithms in the bioinformatics and bioengineering context is automatic clinical decision-making. \u003C/p>","\u003Cp style=\"text-align:justify;\">For these tasks, these are several well-known algorithms (artificial neural networks, classifiers, etc.), which are tuned based on (labeled) samples to optimize the classification of unseen instances. A deep understanding of the mathematical details of the decision behind an Artificial intelligence algorithm may be possible for statistics or computer science domain experts. Clearly, when it comes to the fate of human beings, this \"developer’s explanation\" is not sufficient. \u003C/p>\u003Cp style=\"text-align:justify;\">The shift from therapy-relevant decisions based on human knowledge to black-box-like computer algorithms makes the decision-making increasingly incomprehensible to medical staff and patients. This has been recognized in the issuance of guidelines, e.g., by the European Union or DARPA (USA), which emphasize the need for computer-based decisions to be transparent and in a form that can be communicated in an understandable way to medical personnel and patients. To address this problem, the concept of explainable artificial intelligence (XAI) is attracting scientific interest. XAI uses a representation of human knowledge, usually (a subset of) predicate logic, for its reasoning, deduction, and classification (diagnosis). The aim of this workshop is to boost the research and industrial community in the proposal and development of methodologies aimed to (clearly) explain the clinical decisional process to non-domain experts.\u003C/p>","2024-12-13T23:44:46.223Z","2024-12-24T01:02:27.880Z","2024-12-24T01:02:27.869Z","448",[2681,2683,2685,2687],{"id":2069,"name":2070,"committee":16,"position":16,"affiliation":2071,"email":16,"biography":16,"createdAt":2072,"updatedAt":2072,"url_path_id":2073,"contactPhoto":16,"socialLinks":2682,"url_path":2075},[],{"id":2077,"name":2078,"committee":16,"position":16,"affiliation":2079,"email":16,"biography":16,"createdAt":2080,"updatedAt":2080,"url_path_id":2081,"contactPhoto":16,"socialLinks":2684,"url_path":2083},[],{"id":2085,"name":2086,"committee":16,"position":16,"affiliation":1780,"email":16,"biography":16,"createdAt":2087,"updatedAt":2087,"url_path_id":2088,"contactPhoto":16,"socialLinks":2686,"url_path":2090},[],{"id":2688,"name":2689,"committee":16,"position":16,"affiliation":2690,"email":16,"biography":63,"createdAt":2691,"updatedAt":2691,"url_path_id":2692,"contactPhoto":16,"socialLinks":2693,"url_path":2694},413,"Pan Huang","Chongqing University","2024-12-24T01:02:18.393Z","534",[],"-329","-244",{"id":201,"session":2697},{"id":433,"title":2698,"teaser":2699,"body":2700,"createdAt":2701,"updatedAt":2702,"publishedAt":2703,"url_path_id":2704,"contacts":2705,"url_path":2730},"Explainable Artificial Intelligence Techniques for Open Government","\u003Cp style=\"text-align:justify;\">In the era of data-driven governance, linked open government data (LOGD) plays a crucial role in enhancing transparency, accountability, and public trust. Artificial Intelligence (AI) has demonstrated its potential to extract insights from Open Data, enabling policy-makers and citizens to make informed decisions. However, the opaque nature of many AI models poses significant challenges to their adoption in government and civic contexts, where explainability is paramount. \u003C/p>","\u003Cp style=\"text-align:justify;\">This special session explores Explainable AI (XAI) techniques applied to LOGD data to ensure interpretability, fairness, and accountability in AI-driven governmental systems. \u003C/p>\u003Cp style=\"text-align:justify;\">This session will delve into cutting-edge research and real-world applications, fostering a discussion on the methods, tools, and frameworks needed to make AI robust and transparent for public governance. This session is designed to foster a comprehensive understanding of the role of XAI in advancing open government initiatives. The discussions will explore how XAI can ensure transparency and build public trust in government decision-making processes by emphasizing the need for an interpretable and trustworthy AI system. \u003C/p>\u003Cp style=\"text-align:justify;\">Participants will gain insights into the latest methodologies, focusing on XAI techniques tailored explicitly to analysing and utilizing open government data. Real-world applications will be a key highlight, demonstrating how XAI has effectively improved policy-making and public service delivery. These case studies will underscore the practical benefits and challenges of integrating XAI into governmental systems. The session will also address the multifaceted obstacles—technical, ethical, and organisational—that may arise in this integration process, offering strategies to overcome them. A crucial aspect of the session is to foster collaboration among diverse stakeholders, including researchers, practitioners, and government officials. This platform will encourage the exchange of ideas and the development of partnerships aimed at advancing the adoption of XAI in the public sector. The ultimate goal is to align AI's capabilities with the principles of fairness, accountability, and transparency essential for effective governance.\u003C/p>","2024-12-13T23:44:46.925Z","2024-12-24T01:04:09.353Z","2024-12-24T01:04:09.347Z","449",[2706,2708,2715,2722],{"id":1743,"name":1744,"committee":16,"position":16,"affiliation":1745,"email":16,"biography":16,"createdAt":1746,"updatedAt":1746,"url_path_id":1747,"contactPhoto":16,"socialLinks":2707,"url_path":1749},[],{"id":2709,"name":2710,"committee":16,"position":16,"affiliation":1761,"email":16,"biography":16,"createdAt":2711,"updatedAt":2711,"url_path_id":2712,"contactPhoto":16,"socialLinks":2713,"url_path":2714},241,"Antonella Madau","2024-12-13T23:37:24.147Z","292",[],"-88",{"id":2716,"name":2717,"committee":16,"position":16,"affiliation":1745,"email":16,"biography":16,"createdAt":2718,"updatedAt":2718,"url_path_id":2719,"contactPhoto":16,"socialLinks":2720,"url_path":2721},221,"Agostino Marengo","2024-12-13T23:37:18.609Z","272",[],"-68",{"id":2723,"name":2724,"committee":16,"position":16,"affiliation":2725,"email":16,"biography":16,"createdAt":2726,"updatedAt":2726,"url_path_id":2727,"contactPhoto":16,"socialLinks":2728,"url_path":2729},266,"Debora Montano","University of Modena and Reggio Emilia, Faculty of Medicine and Surgery","2024-12-13T23:37:31.563Z","317",[],"-113","-245",{"id":372,"session":2732},{"id":201,"title":2733,"teaser":2734,"body":2735,"createdAt":2736,"updatedAt":2737,"publishedAt":2738,"url_path_id":2739,"contacts":2740,"url_path":2764},"Explainable Deep Neural Networks for Responsible AI: Post-Hoc and Self-Explaining Approaches (DeepXplain 2025)","\u003Cp style=\"text-align:justify;\">The adoption of Deep Neural Networks (DNNs) in critical domains such as healthcare, governance, and misinformation detection has created an unprecedented demand for high-performance and interpretable models. Despite their success, DNNs' opaque nature undermines user trust and raises ethical concerns, especially in sensitive applications. \u003C/p>","\u003Cp style=\"text-align:justify;\">The need for Explainable Artificial Intelligence (XAI) methods has never been more pressing, and both post-hoc and self-explaining approaches hold promise in addressing this challenge. This special session at IJCNN 2025 aims to bring together researchers and practitioners to explore innovative methodologies that enhance the interpretability of DNNs while maintaining their predictive accuracy. Specific areas of focus include post hoc techniques (e.g. SHAP, LIME, Grad-CAM), self-explaining neural network architectures (e.g. prototype networks, SENNs), and interdisciplinary evaluations of AI systems in terms of fairness, trust, and social impact.\u003C/p>","2024-12-13T23:44:47.602Z","2025-05-03T20:35:42.717Z","2024-12-24T01:05:39.418Z","450",[2741,2749,2756],{"id":2742,"name":2743,"committee":16,"position":16,"affiliation":2744,"email":16,"biography":16,"createdAt":2745,"updatedAt":2745,"url_path_id":2746,"contactPhoto":16,"socialLinks":2747,"url_path":2748},296,"Francielle Vargas","University of São Paulo","2024-12-13T23:37:41.436Z","347",[],"-143",{"id":2750,"name":2751,"committee":16,"position":16,"affiliation":2744,"email":16,"biography":63,"createdAt":2752,"updatedAt":2752,"url_path_id":2753,"contactPhoto":16,"socialLinks":2754,"url_path":2755},562,"Roseli Romero","2025-05-03T20:35:05.004Z","727",[],"-516",{"id":2757,"name":2758,"committee":16,"position":16,"affiliation":2759,"email":16,"biography":63,"createdAt":2760,"updatedAt":2760,"url_path_id":2761,"contactPhoto":16,"socialLinks":2762,"url_path":2763},563,"Jackson Trager","University of Southern California","2025-05-03T20:35:22.300Z","728",[],"-517","-246",{"id":359,"session":2766},{"id":372,"title":2767,"teaser":2768,"body":2769,"createdAt":2770,"updatedAt":2771,"publishedAt":2772,"url_path_id":2773,"contacts":2774,"url_path":2797},"Exploring Advanced Techniques and Applications in AutoML","\u003Cp style=\"text-align:justify;\">The rapid development of machine learning (ML) has led to a wide range of applications in various fields, including healthcare, finance, and natural language processing. However, the success of ML models often relies on extensive expertise in feature engineering, model selection, and hyperparameter tuning. To address this issue, Automated Machine Learning (AutoML) has emerged as a promising approach to democratize AI by automating these complex processes. \u003C/p>","\u003Cp style=\"text-align:justify;\">AutoML views the machine learning task as a configuration search problem (i.e., optimization problem). This approach reduces the machine's reliance on human experts by enabling automatic feature processing, algorithm model selection and modeling, parameter tuning, and other tasks. AutoML has demonstrated to either match or surpass the results of human experts manually fine-tuning parameters in numerous domains, and it can significantly lower the expenses associated with implementing and utilizing machine learning. It has become one of the most popular and cutting-edge research directions in the field of artificial intelligence and machine learning. \u003C/p>\u003Cp style=\"text-align:justify;\">Recently, there has been an emerging development in machine learning area, such as deep learning, multimodal machine learning, and Large Language Models (LLMs), that has significantly impacted the landscape of AutoML. Despite the significant progress in AutoML, there are still many challenges and opportunities that need to be addressed. This special session aims to provide a platform for researchers and practitioners to discuss the latest advancements in AutoML, identify the current challenges and future directions in AutoML, and promote the adoption of AutoML techniques in various domains and industries.\u003C/p>","2024-12-13T23:44:48.256Z","2024-12-24T01:08:35.124Z","2024-12-24T01:08:35.117Z","451",[2775,2783,2790],{"id":2776,"name":2777,"committee":16,"position":16,"affiliation":2778,"email":16,"biography":63,"createdAt":2779,"updatedAt":2779,"url_path_id":2780,"contactPhoto":16,"socialLinks":2781,"url_path":2782},416,"Zhongyi Hu","Wuhan University","2024-12-24T01:08:03.147Z","537",[],"-332",{"id":953,"name":2784,"committee":16,"position":16,"affiliation":2785,"email":16,"biography":63,"createdAt":2786,"updatedAt":2786,"url_path_id":2787,"contactPhoto":16,"socialLinks":2788,"url_path":2789},"Mustafa Misir","Duke Kunshan University","2024-12-24T01:07:47.562Z","536",[],"-331",{"id":2791,"name":2792,"committee":16,"position":16,"affiliation":2645,"email":16,"biography":63,"createdAt":2793,"updatedAt":2793,"url_path_id":2794,"contactPhoto":16,"socialLinks":2795,"url_path":2796},414,"Yi Mei","2024-12-24T01:07:27.824Z","535",[],"-330","-247",{"id":427,"session":2799},{"id":359,"title":2800,"teaser":2801,"body":2802,"createdAt":2803,"updatedAt":2804,"publishedAt":2805,"url_path_id":2806,"contacts":2807,"url_path":2862},"Foundation Models in Medicine (FMM)","\u003Cp style=\"text-align:justify;\">Foundation Models (FMs) represent a significant advancement in deep learning architectures, characterized by their large-scale nature and task-agnostic design. Trained using self-supervised learning on extensive, diverse datasets, these models acquire a generalized understanding applicable across a spectrum of downstream tasks. \u003C/p>","\u003Cp style=\"text-align:justify;\">The motivation for this special session lies in addressing the promises and challenges of FMs in medicine. These models have the potential to revolutionize healthcare by enabling more accurate diagnoses, personalized treatment plans, and streamlined workflows, fundamentally transforming how medicine is practiced. Despite their transformative potential, FMs still face notable limitations, such as the need for extensive datasets, which are often restricted by privacy concerns. Additionally, while FMs exhibit strong generalization, their transferability to specific medical tasks can be hindered by data distribution differences and the inherent complexity of medical data. Interpretability remains another critical challenge, as the complexity of FMs limits the transparency of predictions—crucial in clinical settings where informed decision-making are paramount. \u003C/p>\u003Cp style=\"text-align:justify;\">The objectives for this session include exploring FMs' potential to revolutionize medical applications, from clinical natural language processing to advanced computer vision models for medical imaging analysis and multimodal data integration for personalized medicine, such as creating patient-specific Digital Twins. Addressing the current limitations is crucial for ensuring safer and more effective clinical deployment of FMs, particularly by tackling the technical and ethical challenges inherent to medical data. The collaborative environment of this session aims to foster cross-disciplinary innovation and encourage the development of practical solutions that address the unique challenges posed by AI medical applications. This session aims to foster discussion on recent advancements, share practical insights, and address key challenges in applying FMs to medical applications.\u003C/p>","2024-12-13T23:44:48.923Z","2024-12-24T01:11:12.738Z","2024-12-24T01:11:12.732Z","452",[2808,2816,2824],{"id":2809,"name":2810,"committee":16,"position":16,"affiliation":2811,"email":16,"biography":16,"createdAt":2812,"updatedAt":2812,"url_path_id":2813,"contactPhoto":16,"socialLinks":2814,"url_path":2815},247,"Aurora Rofena","University Campus Bio-Medico of Rome","2024-12-13T23:37:25.840Z","298",[],"-94",{"id":2817,"name":2818,"committee":16,"position":16,"affiliation":2819,"email":16,"biography":63,"createdAt":2820,"updatedAt":2820,"url_path_id":2821,"contactPhoto":16,"socialLinks":2822,"url_path":2823},417,"Matteo Tortora","University of Genoa","2024-12-24T01:11:01.749Z","538",[],"-333",{"id":641,"name":2825,"committee":16,"position":16,"affiliation":2826,"email":16,"biography":63,"createdAt":2827,"updatedAt":2828,"url_path_id":2829,"contactPhoto":2830,"socialLinks":2858,"url_path":2861},"Valerio Guarrasi","Università Campus Bio-Medico di Roma","2024-09-03T15:32:59.223Z","2024-09-04T16:19:42.492Z","44",{"id":750,"name":2831,"alternativeText":16,"caption":16,"width":2832,"height":2832,"formats":2833,"hash":2854,"ext":1029,"mime":1032,"size":2855,"url":2856,"previewUrl":16,"provider":23,"provider_metadata":16,"createdAt":2857,"updatedAt":2857},"picture_1_square.jpg",2250,{"large":2834,"small":2839,"medium":2844,"thumbnail":2849},{"ext":1029,"url":2835,"hash":2836,"mime":1032,"name":2837,"path":16,"size":2838,"width":906,"height":906},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/large_picture_1_square_933086dba4.jpg","large_picture_1_square_933086dba4","large_picture_1_square.jpg",137.35,{"ext":1029,"url":2840,"hash":2841,"mime":1032,"name":2842,"path":16,"size":2843,"width":913,"height":913},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/small_picture_1_square_933086dba4.jpg","small_picture_1_square_933086dba4","small_picture_1_square.jpg",37.83,{"ext":1029,"url":2845,"hash":2846,"mime":1032,"name":2847,"path":16,"size":2848,"width":920,"height":920},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/medium_picture_1_square_933086dba4.jpg","medium_picture_1_square_933086dba4","medium_picture_1_square.jpg",77.64,{"ext":1029,"url":2850,"hash":2851,"mime":1032,"name":2852,"path":16,"size":2853,"width":1047,"height":1047},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/thumbnail_picture_1_square_933086dba4.jpg","thumbnail_picture_1_square_933086dba4","thumbnail_picture_1_square.jpg",5.1,"picture_1_square_933086dba4",580.83,"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/picture_1_square_933086dba4.jpg","2024-09-04T16:19:40.049Z",[2859],{"id":647,"url":2860,"platform":1482},"https://www.unicampus.it/people/valerio-guarrasi/","-24","-248",{"id":195,"session":2864},{"id":427,"title":2865,"teaser":2866,"body":2867,"createdAt":2868,"updatedAt":2869,"publishedAt":2870,"url_path_id":2871,"contacts":2872,"url_path":2884},"Generative AI in Privacy and Security: Challenges and Perspectives","\u003Cp style=\"text-align:justify;\">The rapid advancement of generative AI technologies has brought both transformative potential and unprecedented challenges in the realms of privacy and security. \u003C/p>","\u003Cp style=\"text-align:justify;\">As AI systems become increasingly adept at creating synthetic data, images, and even deepfakes, the boundaries of what constitutes secure and private information are being tested. This track explores the evolving landscape of generative AI, focusing on the complex interplay between innovation, privacy protection, and security threats. We aim to address critical questions such as: How can generative AI compromise personal data? What new security vulnerabilities are emerging, and how can we counteract them? What are the legal and ethical implications of deploying such powerful technologies? And finally, how can generative AI itself be harnessed as a tool for enhancing privacy and strengthening security frameworks? This track will bring together researchers, industry leaders, and policy-makers to discuss cuttingedge developments, share perspectives on key challenges, and explore the potential future directions of generative AI in a secure, privacy-compliant digital world. Through a combination of academic papers, case studies, and panel discussions, we will highlight both the risks and opportunities presented by these powerful tools.\u003C/p>","2024-12-13T23:44:49.625Z","2024-12-24T01:12:47.089Z","2024-12-24T01:12:47.084Z","453",[2873,2880,2882],{"id":2874,"name":2875,"committee":16,"position":16,"affiliation":1780,"email":16,"biography":16,"createdAt":2876,"updatedAt":2876,"url_path_id":2877,"contactPhoto":16,"socialLinks":2878,"url_path":2879},341,"Lelio Campanile","2024-12-13T23:38:01.185Z","392",[],"-188",{"id":2085,"name":2086,"committee":16,"position":16,"affiliation":1780,"email":16,"biography":16,"createdAt":2087,"updatedAt":2087,"url_path_id":2088,"contactPhoto":16,"socialLinks":2881,"url_path":2090},[],{"id":2069,"name":2070,"committee":16,"position":16,"affiliation":2071,"email":16,"biography":16,"createdAt":2072,"updatedAt":2072,"url_path_id":2073,"contactPhoto":16,"socialLinks":2883,"url_path":2075},[],"-249",{"id":446,"session":2886},{"id":195,"title":2887,"teaser":2888,"body":2889,"createdAt":2890,"updatedAt":2891,"publishedAt":2892,"url_path_id":2893,"contacts":2894,"url_path":2926},"GPAIT2: General Purpose Artificial Intelligence Technologies and Trustworthiness","\u003Cp style=\"text-align:justify;\">In Artificial Intelligence, there is an increasing demand for adaptive models capable of dealing with a diverse spectrum of learning tasks, surpassing the limitations of systems designed to tackle a single task. \u003C/p>","\u003Cp style=\"text-align:justify;\">The term General Purpose Artificial Intelligence Systems (GPAIS) refers to these AI systems. To date, the possibility of an Artificial General Intelligence, powerful enough to perform any intellectual task as if it were human, or even improve it, has remained an aspiration, fiction, and even considered a risk for our society in the light of the fast evolution of modern AI systems. Whilst we might still be far from reaching this paradigm, GPAIS is a reality and sitting at the forefront of AI research. \u003C/p>\u003Cp style=\"text-align:justify;\">Deep Learning has played a key role in the success of these general-purpose systems. The rise of foundation models trained on broad data via a self-supervised approach have shown great potential to then adapt (fine-tune) to a wide range of downstream tasks.  In addition to foundation models, to realise GPAIS, we may also highlight the use of other AI systems to either design or enrich an existing AI system, so that it may generalise further.  In a nutshell, we may construct or enhance AI with an additional AI stage. A common example of this is to make AI learn to work like an AI expert, determining which algorithms and/or components are most suitable for a given problem.\u003Cbr>\u003Cbr>Among others, one may expect a GPAIS to be able to transfer knowledge from similar tasks, learn with as little data as possible, and rapidly adapt to changes and/or new tasks. These properties are typically needed in a wide range of research areas such as AutoML, few-shot learning, weakly supervised learning, or continual learning, some of which are solved by meta-learning, reinforcement learning or evolutionary computation. To advance in the field of GPAIS, it is crucial to explore open-world approaches that enable systems to operate in dynamic and unfamiliar environments, where new tasks are dealt with limited data, exploiting as much as possible previous knowledge. \u003C/p>\u003Cp style=\"text-align:justify;\">While current GPAIS offerings already provide numerous functionalities, they also come with certain risks. The ability of these systems to process vast amounts of data and make automated decisions raises concerns regarding privacy, ethics, and fairness in their implementation. Recent research efforts in AI are focused on developing techniques and frameworks that enhance oversight, transparency, interpretability, and robustness, among others, with the aim of designing responsible AI systems. Those efforts become even more needed when developing GPAIS. This special session aims to foster research on Trustworthy and Explainable AI for GPAIS.\u003C/p>","2024-12-13T23:44:50.317Z","2024-12-24T01:15:35.096Z","2024-12-24T01:15:35.092Z","454",[2895,2903,2910,2918],{"id":2896,"name":2897,"committee":16,"position":16,"affiliation":2898,"email":16,"biography":16,"createdAt":2899,"updatedAt":2899,"url_path_id":2900,"contactPhoto":16,"socialLinks":2901,"url_path":2902},317,"Isaac Triguero","University of Granada","2024-12-13T23:37:49.976Z","368",[],"-164",{"id":2904,"name":2905,"committee":16,"position":16,"affiliation":2744,"email":16,"biography":63,"createdAt":2906,"updatedAt":2906,"url_path_id":2907,"contactPhoto":16,"socialLinks":2908,"url_path":2909},418,"Ricardo Cerri","2024-12-24T01:14:49.956Z","539",[],"-334",{"id":2911,"name":2912,"committee":16,"position":16,"affiliation":2913,"email":16,"biography":63,"createdAt":2914,"updatedAt":2914,"url_path_id":2915,"contactPhoto":16,"socialLinks":2916,"url_path":2917},419,"Tomas Horvath","Edinburgh Napier University","2024-12-24T01:15:10.734Z","540",[],"-335",{"id":2919,"name":2920,"committee":16,"position":16,"affiliation":2921,"email":16,"biography":16,"createdAt":2922,"updatedAt":2922,"url_path_id":2923,"contactPhoto":16,"socialLinks":2924,"url_path":2925},285,"Felipe Kenji Nakano","KU Leuven KULAK","2024-12-13T23:37:37.631Z","336",[],"-132","-250",{"id":103,"session":2928},{"id":446,"title":2929,"teaser":2930,"body":2931,"createdAt":2932,"updatedAt":2933,"publishedAt":2934,"url_path_id":2935,"contacts":2936,"url_path":2975},"Graph-based solutions for Artificial Intelligence","\u003Cp style=\"text-align:justify;\">Graphs are particularly well-suited for representing interacting systems, as they excel at capturing structural dependencies. This versatility has made graphs a powerful tool for modeling a wide range of phenomena, from the structures of molecular compounds to the dynamic interactions within social networks, as well as the complexities of transportation systems.\u003C/p>","\u003Cp style=\"text-align:justify;\"> Deep learning models have not been excluded from this trend, as graphs can represent several aspects of their structure. Some examples include: (i) computational graphs, where nodes represent operations and edges illustrate the flow of data between operations; (ii) dependency graphs in attention mechanisms of transformer models, which capture relationships between tokens; (iii) complex networks, which model deep learning networks to map information flow. These are just a few examples of the versatility of graph-based representations in deep learning. The potential of graphs to further enhance the representation and understanding of deep learning models remains largely unexplored, which offers many opportunities for addressing open challenges in this area. For instance, one significant issue is the reduction of model size, which is crucial for speeding up both training and inference. \u003C/p>\u003Cp style=\"text-align:justify;\">This, in turn, can contribute to lowering the environmental impact of deep learning applications. Another critical challenge is model explainability, which can be addressed through the inherent ability of graphs to naturally represent information flow or feature interactions. Additionally, Generative AI can benefit from graph-based approaches; in fact, graph structures, like Knowledge Graphs, allow for external knowledge injection within Generative AI models. This makes it possible to overcome different limitations, such as hallucinations and lack of knowledge. \u003C/p>\u003Cp style=\"text-align:justify;\">These examples of open issues addressed by graphs highlight their vast opportunities to innovate and enhance this research area. This special session is specifically designed to showcase the potential of graph-based approaches in addressing some of the challenges in deep learning. The focus lies in demonstrating how the inherent flexibility of graph structures—such as traditional graphs, multiplex networks, or multilayer networks—can be leveraged to effectively manage and overcome these challenges. By highlighting innovative techniques and methodologies, this session aims to bridge the gap between graph theory and deep learning, offering a unique perspective within this rapidly evolving field. \u003C/p>\u003Cp style=\"text-align:justify;\">The potential impact of these approaches is relevant in different domains, including construction and manufacturing, where they enable predictive maintenance by analyzing sensor data. This leads to the reduction of downtime and project costs, the enhancement of quality control through image-based anomaly detection, the improvement of product quality and the reduction of waste, which makes it possible to preserve the safety of workers and increase sustainability. Additionally, these approaches power robotics and automation for precision, guaranteeing flexibility and productivity in tasks like assembly and welding.\u003C/p>","2024-12-13T23:44:50.992Z","2024-12-24T01:17:48.734Z","2024-12-24T01:17:48.730Z","455",[2937,2945,2953,2961,2968],{"id":2938,"name":2939,"committee":16,"position":16,"affiliation":2940,"email":16,"biography":16,"createdAt":2941,"updatedAt":2941,"url_path_id":2942,"contactPhoto":16,"socialLinks":2943,"url_path":2944},347,"Luca Virgili","Università Politecnica delle Marche","2024-12-13T23:38:05.014Z","398",[],"-194",{"id":2946,"name":2947,"committee":16,"position":16,"affiliation":2948,"email":16,"biography":16,"createdAt":2949,"updatedAt":2949,"url_path_id":2950,"contactPhoto":16,"socialLinks":2951,"url_path":2952},229,"Alessia Amelio","Università degli Studi \"G. d'Annunzio\" Chieti – Pescara","2024-12-13T23:37:20.747Z","280",[],"-76",{"id":2954,"name":2955,"committee":16,"position":16,"affiliation":2956,"email":16,"biography":16,"createdAt":2957,"updatedAt":2957,"url_path_id":2958,"contactPhoto":16,"socialLinks":2959,"url_path":2960},273,"Eliezer Zahid Gill","Università degli Studi \"G. d'Annunzio\" Chieti – Pescara ","2024-12-13T23:37:33.730Z","324",[],"-120",{"id":2962,"name":2963,"committee":16,"position":16,"affiliation":2940,"email":16,"biography":63,"createdAt":2964,"updatedAt":2964,"url_path_id":2965,"contactPhoto":16,"socialLinks":2966,"url_path":2967},420,"Michele Marchetti","2024-12-24T01:17:39.869Z","541",[],"-336",{"id":2969,"name":2970,"committee":16,"position":16,"affiliation":2940,"email":16,"biography":16,"createdAt":2971,"updatedAt":2971,"url_path_id":2972,"contactPhoto":16,"socialLinks":2973,"url_path":2974},270,"Domenico Ursino","2024-12-13T23:37:32.741Z","321",[],"-117","-251",{"id":717,"session":2977},{"id":103,"title":2978,"teaser":2979,"body":2980,"createdAt":2981,"updatedAt":2982,"publishedAt":2983,"url_path_id":2984,"contacts":2985,"url_path":3010},"Graph/Hypergraph Neural Networks for Structural Analysis","\u003Cp style=\"text-align:justify;\">Graph data is prevalent across diverse fields such as social networks, bioinformatics, transportation systems, recommendation engines, and communication networks. These complex data structures inherently capture intricate relationships and interdependencies that traditional artificial intelligence methods struggle to fully leverage due to their structural complexity. \u003C/p>","\u003Cp style=\"text-align:justify;\">Graph learning has emerged as a pivotal technology designed to effectively analyze and process graph-structured data, offering powerful tools to model and understand the nuances of interconnected systems. This special session aims to showcase cutting-edge foundational theories, novel algorithms, and pioneering applications in graph learning, fostering collaboration and knowledge exchange between academia and industry. \u003C/p>\u003Cp style=\"text-align:justify;\">By bringing together researchers and practitioners, we seek to address current challenges, share insights, and explore future directions in this rapidly evolving field. We plan to delve into theoretical advancements that enhance the expressiveness, generalization, and convergence properties of graph neural networks. Additionally, the session will highlight innovative algorithms and architectures, including attention-based models, graph transformers, and hybrid approaches that push the boundaries of current methodologies. Our focus extends to practical applications that demonstrate the transformative potential of graph learning across various domains. In bioinformatics and chemistry, for instance, graph learning facilitates molecule property prediction, protein interaction analysis, and drug discovery. \u003C/p>\u003Cp style=\"text-align:justify;\">In social network analysis, it aids in community detection, influence propagation modeling, and misinformation spread prevention. The integration of graph learning with computer vision and natural language processing opens new avenues for tasks like scene understanding, semantic parsing, and knowledge graph completion. By addressing real-world problems, we aim to illustrate how graph learning enhances model performance and interpretability, offering tangible benefits.\u003C/p>","2024-12-13T23:44:51.645Z","2024-12-24T07:48:13.643Z","2024-12-24T07:48:13.638Z","456",[2986,2994,3002],{"id":2987,"name":2988,"committee":16,"position":16,"affiliation":2989,"email":16,"biography":63,"createdAt":2990,"updatedAt":2990,"url_path_id":2991,"contactPhoto":16,"socialLinks":2992,"url_path":2993},421,"Shihui Ying","Shanghai University","2024-12-24T07:47:20.320Z","542",[],"-337",{"id":2995,"name":2996,"committee":16,"position":16,"affiliation":2997,"email":16,"biography":63,"createdAt":2998,"updatedAt":2998,"url_path_id":2999,"contactPhoto":16,"socialLinks":3000,"url_path":3001},422,"Mingxia Liu","University of North Carolina at Chapel Hill","2024-12-24T07:47:38.076Z","543",[],"-338",{"id":3003,"name":3004,"committee":16,"position":16,"affiliation":3005,"email":16,"biography":63,"createdAt":3006,"updatedAt":3006,"url_path_id":3007,"contactPhoto":16,"socialLinks":3008,"url_path":3009},423,"Xiangmin Han","Tsinghua University","2024-12-24T07:47:53.300Z","544",[],"-339","-252",{"id":464,"session":3012},{"id":717,"title":3013,"teaser":3014,"body":3015,"createdAt":3016,"updatedAt":3017,"publishedAt":3018,"url_path_id":3019,"contacts":3020,"url_path":3039},"Human-Centered Artificial Intelligence (HCAI)","\u003Cp style=\"text-align:justify;\">Human-centered Artificial Intelligence (AI) represents a paradigm shift in the development and deployment of AI technologies, emphasizing the augmentation, complementarity, and enhancement of human capabilities, rather than replacing them. This approach intertwines the technical prowess of AI with ethical, social, and human values, ensuring that AI advancements are not only effective but also beneficial and accessible to all segments of society. \u003C/p>","\u003Cp style=\"text-align:justify;\">Human-centered AI marks a departure from traditional AI models that primarily focus on simulating human intelligence in isolation. Instead, it fosters a synergy between human andmachine intelligence, overcoming the limitations inherent in each. This approach leads to AI solutions that increase human well-being, respect privacy, adhere to responsible design principles, and are subject to robust governance and oversight. By embracing these principles, AI can interact respectfully with individuals, honoring their cognitive capacities and societal contexts. \u003C/p>\u003Cp style=\"text-align:justify;\">This drives the AI community to face new challenges aimed at improving human satisfaction when they interact with intelligent systems, encompassing some key aspects: Ethical and Privacy Considerations: As AI becomes increasingly pervasive, addressing concerns like privacy and ethical design is paramount. Solutions must prioritize these aspects while maintaining efficiency and effectiveness. Additionally, the development of responsible and human-compatible AI includes the need to understand how people engage with and trust AI systems. There’s also a need to explain the operation of AI models and improve people’s understanding of how AI systems operate. Interoperability in Diverse Environments: Unlike the predictable Cloud environment, personalized AI systems need to operate across heterogeneous devices. This necessitates AI solutions that are adaptable to dynamic contexts, varying data availability, and connectivity challenges. Enhanced User Experiences: With the rise of Large Language Models and conversational user interfaces, advanced dialogue systems have grown in popularity, and many intelligent assistants are being developed for business, social, industrial, sanitary, and even emotional purposes. Therefore the definition of adequate methodological approaches to design this new kind of system is nowadays even more critical. In the backdrop of these human-centric considerations, technical challenges such as reducing communication overhead, latency, and energy consumption remain critical, especially when AI systems operate close to the physical generation and collection of data. \u003C/p>\u003Cp style=\"text-align:justify;\">The special session seeks to advance research on human-centered Artificial intelligence. It invites contributions from researchers and practitioners interested in improving the interaction of humans with AI solutions, emphasizing both foundational aspects and practical applications. The goal is to foster collaboration among research communities to stimulate the development of advanced artificial intelligence approaches applicable across various computing and communication domains. For this reason, this special session also welcomes high-quality interdisciplinary contributions related to applications in health, well-being, industry 5.0, environmental control/monitoring, computer vision, smart cities, smart agriculture, smart distance education, and self-driving vehicles.\u003C/p>","2024-12-13T23:44:52.258Z","2025-01-10T13:44:29.497Z","2024-12-24T07:49:36.768Z","457",[3021,3029,3037],{"id":3022,"name":3023,"committee":16,"position":16,"affiliation":3024,"email":16,"biography":16,"createdAt":3025,"updatedAt":3025,"url_path_id":3026,"contactPhoto":16,"socialLinks":3027,"url_path":3028},240,"Anna Vacca","UnitelmaSapienza","2024-12-13T23:37:23.852Z","291",[],"-87",{"id":3030,"name":3031,"committee":16,"position":16,"affiliation":3032,"email":16,"biography":63,"createdAt":3033,"updatedAt":3033,"url_path_id":3034,"contactPhoto":16,"socialLinks":3035,"url_path":3036},464,"Marta Cimitile","UnitelmaSapienza University ","2025-01-10T13:43:38.130Z","598",[],"-392",{"id":1998,"name":1999,"committee":16,"position":16,"affiliation":1761,"email":16,"biography":63,"createdAt":2000,"updatedAt":2000,"url_path_id":2001,"contactPhoto":16,"socialLinks":3038,"url_path":2003},[],"-253",{"id":481,"session":3041},{"id":464,"title":3042,"teaser":3043,"body":63,"createdAt":3044,"updatedAt":3045,"publishedAt":3046,"url_path_id":3047,"contacts":3048,"url_path":3057},"Human-like Intelligence","\u003Cp>The special session will focus on the current research trends in theory and practical aspects of systems that enhance and complement Computational Intelligence (CI) and Artificial Intelligence (AI) technologies to design and develop cognitive architectures enabling learning and abstraction abilities, and intelligent systems capable of human-like language understanding.\u003C/p>","2024-12-13T23:44:52.946Z","2024-12-24T08:02:49.953Z","2024-12-24T08:02:49.949Z","458",[3049],{"id":3050,"name":3051,"committee":16,"position":16,"affiliation":3052,"email":16,"biography":63,"createdAt":3053,"updatedAt":3053,"url_path_id":3054,"contactPhoto":16,"socialLinks":3055,"url_path":3056},424,"Marek Reformat","University of Alberta","2024-12-24T08:02:39.404Z","545",[],"-340","-254",{"id":1120,"session":3059},{"id":481,"title":3060,"teaser":63,"body":63,"createdAt":3061,"updatedAt":3062,"publishedAt":3063,"url_path_id":3064,"contacts":3065,"url_path":3073},"Hyperdimensional Computing and Vector Symbolic Architectures for Neural Networks and Artificial Intelligence","2024-12-13T23:44:53.613Z","2024-12-24T08:03:47.490Z","2024-12-24T08:03:47.483Z","459",[3066],{"id":3067,"name":3068,"committee":16,"position":16,"affiliation":1522,"email":16,"biography":16,"createdAt":3069,"updatedAt":3069,"url_path_id":3070,"contactPhoto":16,"socialLinks":3071,"url_path":3072},244,"Antonello Rosato","2024-12-13T23:37:25.028Z","295",[],"-91","-255",{"id":1055,"session":3075},{"id":1120,"title":3076,"teaser":3077,"body":3078,"createdAt":3079,"updatedAt":3080,"publishedAt":3081,"url_path_id":3082,"contacts":3083,"url_path":3123},"Integrated Machine Learning and Wireless Communication (IMAC)","\u003Cp style=\"text-align:justify;\">The Integrated Machine Learning and Wireless Communication (IMAC) special session at IJCNN 2025 aims to address the critical convergence of machine learning (ML) and wireless communication, which is a nexus pivotal to future AI applications and the next-generation networks. \u003C/p>","\u003Cp style=\"text-align:justify;\">As AI capabilities surge and the proliferation of connected devices accelerates, there is an unprecedented demand for wireless networks to seamlessly support advanced AI applications with low latency. Meanwhile, the ever-growing complexity of future networks along with limited wireless and energy resources, warrants the pressing need to harmonize ML innovations with wireless networks to meet the demands of intelligent applications such as autonomous vehicles, augmented and virtual reality, and smart city ecosystems. In view of these, the primary objective of this special session is to foster collaboration between the ML and wireless communication communities, bridging the gap between data-centric AI applications and the resource-constrained/heterogeneous environments of wireless networks. By emphasizing both “ML for Wireless Communication” and “Wireless Communication for ML,” IMAC will explore how ML enhances wireless network capabilities while advanced wireless infrastructures simultaneously support and scale ML applications.\u003C/p>","2024-12-13T23:44:54.383Z","2024-12-24T08:06:49.406Z","2024-12-24T08:06:49.400Z","460",[3084,3092,3099,3107,3115],{"id":3085,"name":3086,"committee":16,"position":16,"affiliation":3087,"email":16,"biography":16,"createdAt":3088,"updatedAt":3088,"url_path_id":3089,"contactPhoto":16,"socialLinks":3090,"url_path":3091},323,"Jihong Park","Singapore University of Technology and Design","2024-12-13T23:37:52.557Z","374",[],"-170",{"id":3093,"name":3094,"committee":16,"position":16,"affiliation":3087,"email":16,"biography":63,"createdAt":3095,"updatedAt":3095,"url_path_id":3096,"contactPhoto":16,"socialLinks":3097,"url_path":3098},425,"Zihan Chen","2024-12-24T08:05:39.665Z","546",[],"-341",{"id":3100,"name":3101,"committee":16,"position":16,"affiliation":3102,"email":16,"biography":16,"createdAt":3103,"updatedAt":3103,"url_path_id":3104,"contactPhoto":16,"socialLinks":3105,"url_path":3106},325,"Jinho Choi","University of Adelaide","2024-12-13T23:37:53.493Z","376",[],"-172",{"id":3108,"name":3109,"committee":16,"position":16,"affiliation":3110,"email":16,"biography":63,"createdAt":3111,"updatedAt":3111,"url_path_id":3112,"contactPhoto":16,"socialLinks":3113,"url_path":3114},426,"Seung-Woo Ko","Inha University","2024-12-24T08:05:55.051Z","547",[],"-342",{"id":3116,"name":3117,"committee":16,"position":16,"affiliation":3118,"email":16,"biography":63,"createdAt":3119,"updatedAt":3119,"url_path_id":3120,"contactPhoto":16,"socialLinks":3121,"url_path":3122},427,"Seong-Lyun Kim","Yonsei University","2024-12-24T08:06:10.530Z","548",[],"-343","-256",{"id":539,"session":3125},{"id":1055,"title":3126,"teaser":3127,"body":3128,"createdAt":3129,"updatedAt":3130,"publishedAt":3131,"url_path_id":3132,"contacts":3133,"url_path":3182},"Intelligent Vehicles and Transportation Systems (IVTS)","\u003Cp style=\"text-align:justify;\">The research and development of intelligent vehicles and transportation systems are rapidly growing worldwide. Intelligent transportation systems are making transformative changes in all aspects of surface transportation based on vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I) connectivity, and automated driving (AV). \u003C/p>","\u003Cp style=\"text-align:justify;\">With the support of advanced equipment, a host of intelligent devices in cars have made various functions in practice, such as airbag control, unwelcome intrusion detection, collision warning and avoidance, power management and navigation, driver alertness monitoring, etc. Among those functions, the neural network plays a critical role in building all types and levels of intelligence in vehicle and transportation systems. The objective of this special session is to provide a forum for researchers and practitioners to present advanced research in neural network models with a focus on innovative applications for intelligent vehicle and transportation systems. This session seeks contributions on the latest developments and emerging research in all aspects of intelligent vehicle and transportation systems.\u003C/p>","2024-12-13T23:44:55.210Z","2024-12-24T08:09:12.113Z","2024-12-24T08:09:12.108Z","461",[3134,3142,3150,3158,3166,3174],{"id":3135,"name":3136,"committee":16,"position":16,"affiliation":3137,"email":16,"biography":63,"createdAt":3138,"updatedAt":3138,"url_path_id":3139,"contactPhoto":16,"socialLinks":3140,"url_path":3141},428,"Yi Murphey","University of Michigan-Dearborn","2024-12-24T08:08:24.200Z","549",[],"-344",{"id":3143,"name":3144,"committee":16,"position":16,"affiliation":3145,"email":16,"biography":63,"createdAt":3146,"updatedAt":3146,"url_path_id":3147,"contactPhoto":16,"socialLinks":3148,"url_path":3149},429,"Xian Wei","ECNU","2024-12-24T08:08:44.480Z","550",[],"-345",{"id":3151,"name":3152,"committee":16,"position":16,"affiliation":3153,"email":16,"biography":16,"createdAt":3154,"updatedAt":3154,"url_path_id":3155,"contactPhoto":16,"socialLinks":3156,"url_path":3157},334,"Justin Dauwels","Delft University of Technology","2024-12-13T23:37:57.660Z","385",[],"-181",{"id":3159,"name":3160,"committee":16,"position":16,"affiliation":3161,"email":16,"biography":16,"createdAt":3162,"updatedAt":3162,"url_path_id":3163,"contactPhoto":16,"socialLinks":3164,"url_path":3165},310,"Hao Shen","Fortiss GmbH","2024-12-13T23:37:46.867Z","361",[],"-157",{"id":3167,"name":3168,"committee":16,"position":16,"affiliation":3169,"email":16,"biography":16,"createdAt":3170,"updatedAt":3170,"url_path_id":3171,"contactPhoto":16,"socialLinks":3172,"url_path":3173},277,"Enrique Dominguez","University of Malaga","2024-12-13T23:37:35.021Z","328",[],"-124",{"id":3175,"name":3176,"committee":16,"position":16,"affiliation":3177,"email":16,"biography":16,"createdAt":3178,"updatedAt":3178,"url_path_id":3179,"contactPhoto":16,"socialLinks":3180,"url_path":3181},289,"Finn Tseng","Ford Motor Company","2024-12-13T23:37:38.998Z","340",[],"-136","-257",{"id":1123,"session":3184},{"id":539,"title":3185,"teaser":3186,"body":3187,"createdAt":3188,"updatedAt":3189,"publishedAt":3190,"url_path_id":3191,"contacts":3192,"url_path":3243},"Leveraging Foundation Models for Efficiently Developing Generative Models","\u003Cp style=\"text-align:justify;\">Recent years have witnessed remarkable advancements in foundation models in various domains. Trained on large-scale diverse datasets in a self-supervised manner, these models serve as a basis for various downstream tasks, offering adaptability and robustness. \u003C/p>","\u003Cp style=\"text-align:justify;\">Although the cost of training such foundation models is not trivial, once these models are trained, they can be repeatedly used for many purposes, reducing the total cost and energy consumption in the end. In this special session, we explore how we can leverage foundation models for efficiently developing generative models.  Although most generative models are trained in a self-supervised manner and do not need human annotations for training, training of generative models from scratch requires vast amounts of compute. Techniques for reducing the cost required for training generative models are beneficial to not only practitioners but also the natural environment. Many studies have addressed this issue. \u003C/p>\u003Cp style=\"text-align:justify;\">One of the most commonly used techniques is Projected GAN, which makes GAN training process efficient by projecting generated and real samples into a fixed, pretrained feature space. This technique is being applied to large-scale GANs and diffusion distillation. On the other hand, there is an attempt to utilize a pretrained foundation model for generators as well. GALIP leverages the pretrained CLIP model in not only its discriminator but also its generator. \u003C/p>\u003Cp style=\"text-align:justify;\">A CLIP-empowered generator induces the visual concepts from CLIP. The CLIP-integrated generator and discriminator boost training efficiency, and as a result, their model only requires about 3% training data and 6% learnable arameters, achieving comparable results to large pretrained autoregressive and diffusion models. In another line, many studies have tried to adopt pretrained generative models for other purposes different from the original one. Progressive Growing of Diffusion Autoencoder (PaGoDA) uses a pre-trained, low-resolution diffusion model to deterministically encode high-resolution data to a structured latent space by solving the PF-ODE forward in time (data-to-noise), starting from a down-sampled image. Using this frozen encoder in an auto-encoder framework, they trained a decoder by progressively growing its resolution. From the nature of progressively growing decoder, PaGoDA avoids re-training teacher/student models when upsampling the student model, which makes the whole training pipeline much cheaper. NExT-GPT [4] is an any-to-any MM-LLM system that can perceive inputs and generate outputs in arbitrary combinations of text, images, videos, and audio. \u003C/p>\u003Cp style=\"text-align:justify;\">By leveraging the existing well-trained encoders and decoders, NExT-GPT is tuned with only a small amount of parameter (1%) of certain projection layers, resulting in low-cost training. Xing et al. proposed to bridge off-the-shelf video or audio generation models with a multimodality latent aligner based on the pre-trained ImageBind model. Through carefully designed optimization strategy and loss functions, they demonstrated joint video-audio generation, visual-steered audio generation, and audio-steered visual generation. In this special session, we further explore how we can use foundation models for reducing the cost for training generative models.\u003C/p>","2024-12-13T23:44:55.975Z","2024-12-24T08:11:36.741Z","2024-12-24T08:11:36.729Z","462",[3193,3201,3208],{"id":3194,"name":3195,"committee":16,"position":16,"affiliation":3196,"email":16,"biography":63,"createdAt":3197,"updatedAt":3197,"url_path_id":3198,"contactPhoto":16,"socialLinks":3199,"url_path":3200},430,"Takashi Shibuya","Sony AI","2024-12-24T08:11:08.033Z","551",[],"-346",{"id":3202,"name":3203,"committee":16,"position":16,"affiliation":1522,"email":16,"biography":16,"createdAt":3204,"updatedAt":3204,"url_path_id":3205,"contactPhoto":16,"socialLinks":3206,"url_path":3207},263,"Danilo Comminiello","2024-12-13T23:37:30.649Z","314",[],"-110",{"id":730,"name":3209,"committee":16,"position":16,"affiliation":3210,"email":16,"biography":63,"createdAt":3211,"updatedAt":3212,"url_path_id":3213,"contactPhoto":3214,"socialLinks":3239,"url_path":3242},"Yuki Mitsufuji","Sony Group Corporation","2024-09-03T15:10:40.838Z","2024-09-04T17:38:25.725Z","35",{"id":1733,"name":3215,"alternativeText":16,"caption":16,"width":3216,"height":3217,"formats":3218,"hash":3235,"ext":1029,"mime":1032,"size":3236,"url":3237,"previewUrl":16,"provider":23,"provider_metadata":16,"createdAt":3238,"updatedAt":3238},"Yuki_Mitsufuji_2022_120x150 (1).jpg",648,810,{"small":3219,"medium":3224,"thumbnail":3230},{"ext":1029,"url":3220,"hash":3221,"mime":1032,"name":3222,"path":16,"size":3223,"width":2348,"height":913},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/small_Yuki_Mitsufuji_2022_120x150_1_4ff0e3a666.jpg","small_Yuki_Mitsufuji_2022_120x150_1_4ff0e3a666","small_Yuki_Mitsufuji_2022_120x150 (1).jpg",20.66,{"ext":1029,"url":3225,"hash":3226,"mime":1032,"name":3227,"path":16,"size":3228,"width":3229,"height":920},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/medium_Yuki_Mitsufuji_2022_120x150_1_4ff0e3a666.jpg","medium_Yuki_Mitsufuji_2022_120x150_1_4ff0e3a666","medium_Yuki_Mitsufuji_2022_120x150 (1).jpg",39.73,600,{"ext":1029,"url":3231,"hash":3232,"mime":1032,"name":3233,"path":16,"size":3234,"width":842,"height":1047},"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/thumbnail_Yuki_Mitsufuji_2022_120x150_1_4ff0e3a666.jpg","thumbnail_Yuki_Mitsufuji_2022_120x150_1_4ff0e3a666","thumbnail_Yuki_Mitsufuji_2022_120x150 (1).jpg",3.98,"Yuki_Mitsufuji_2022_120x150_1_4ff0e3a666",45.44,"https://confcats-siteplex.s3.us-east-1.amazonaws.com/ijcnn25/Yuki_Mitsufuji_2022_120x150_1_4ff0e3a666.jpg","2024-09-04T17:38:23.007Z",[3240],{"id":1733,"url":3241,"platform":1482},"https://www.yukimitsufuji.com/","-15","-258",{"id":600,"session":3245},{"id":1123,"title":3246,"teaser":3247,"body":3248,"createdAt":3249,"updatedAt":3250,"publishedAt":3251,"url_path_id":3252,"contacts":3253,"url_path":3283},"Leveraging Large Language Models for Healthcare Innovation","\u003Cp style=\"text-align:justify;\">Large Language Models (LLMs) demonstrate a significant breakthrough in artificial intelligence (AI), revolutionizing wide range of fields such as machine learning (ML), human computer interaction (HCI), natural language understanding (NLU), natural language generation (NLG), content generation and personalization, domain-specific code generation. \u003C/p>","\u003Cp style=\"text-align:justify;\">These models have gained prominence due to their ability to understand and generate human-like text, enabling a wide range of applications from language translation to content generation and more. Building on the success of Transformer-based models like BERT and GPT, there has been a strong move towards creating even larger and more advanced models, such as GPT-3 and T5. \u003C/p>\u003Cp style=\"text-align:justify;\">At the same time, researchers have developed instruction fine-tuning, a method that uses a variety of prompts across different datasets and tasks to steer the model through both training and generation. This technique allows the model to perform a broad spectrum of tasks within a unified framework. Instruction-finetuned LLMs, such as Generative Pre-Trained Transformers (GPT-4), Pathways Language Model (PaLM), Fine-tuned LAnguage Net - Text-To-Text Transfer Transformer (FLAN-T5), Large Language Model Meta AI (LLaMA), and Alpaca, boast tens to hundreds of billions of parameters and have demonstrated remarkable performance in areas like question answering, logical reasoning, and machine translation. Researchers have investigated the potential of LLMs in healthcare settings. For instance, researchers have fine-tuned PaLM-2 for medical applications on the Medical Text Question and Answer Dataset (MedQA) dataset. Similarly, LLaMA was fine-tuned using medical papers and demonstrated promising results across several biomedical QA datasets. \u003C/p>\u003Cp style=\"text-align:justify;\">A few researchers have examined the use of LLMs in public health scenarios. Additionally, medical language model was trained on unstructured clinical notes from electronic health records and fine-tuned it for a variety of clinical and operational predictive tasks. Their evaluation suggests that this model is versatile for different clinical applications. Additionally, some researchers have utilized pretrained LLMs for detecting mental disorders and performing sentiment analysis using social media data. While LLMs have shown remarkable potential in the healthcare sector, several challenges must be overcome before they can be effectively implemented in this field. In healthcare settings, particularly for decision-making, patient interaction, sentiment analysis, mental health, virtual assistance in healthcare and documentation. LLMs face several critical issues such as reliability, transparency, bias (algorithmic and data) management and correct interpretation of the outcomes. Without thorough validation, LLM-based systems are risky that might provide inaccurate medical information, which could result in harmful misdiagnoses or treatment errors. Furthermore, their responses are often too brief, lacking transparency, reasoning, and proper source references. Therefore, difficult to interpret accurately. This special session aims to explore the most recent advancements in applying LLMs to healthcare, a rapidly advancing field that relies heavily on neural networks (specifically transformer based deep neural networks) as a cornerstone of computational intelligence. Our goal is to assess the challenges and opportunities of utilizing LLMs to discover the most effective solutions in healthcare.\u003C/p>","2024-12-13T23:44:56.819Z","2024-12-24T08:13:59.146Z","2024-12-24T08:13:59.141Z","463",[3254,3261,3269,3276],{"id":965,"name":3255,"committee":16,"position":16,"affiliation":3256,"email":16,"biography":16,"createdAt":3257,"updatedAt":3257,"url_path_id":3258,"contactPhoto":16,"socialLinks":3259,"url_path":3260},"Hari Pandey","Bournemouth University","2024-12-13T23:37:47.766Z","363",[],"-159",{"id":3262,"name":3263,"committee":16,"position":16,"affiliation":3264,"email":16,"biography":63,"createdAt":3265,"updatedAt":3265,"url_path_id":3266,"contactPhoto":16,"socialLinks":3267,"url_path":3268},432,"Niki van Stein","Leiden University","2024-12-24T08:13:40.026Z","553",[],"-348",{"id":3270,"name":3271,"committee":16,"position":16,"affiliation":1349,"email":16,"biography":16,"createdAt":3272,"updatedAt":3272,"url_path_id":3273,"contactPhoto":16,"socialLinks":3274,"url_path":3275},253,"Catarina Moreira","2024-12-13T23:37:27.565Z","304",[],"-100",{"id":3277,"name":3278,"committee":16,"position":16,"affiliation":3256,"email":16,"biography":63,"createdAt":3279,"updatedAt":3279,"url_path_id":3280,"contactPhoto":16,"socialLinks":3281,"url_path":3282},431,"Yan Gong","2024-12-24T08:13:19.857Z","552",[],"-347","-259",{"id":582,"session":3285},{"id":600,"title":3286,"teaser":3287,"body":3288,"createdAt":3289,"updatedAt":3290,"publishedAt":3291,"url_path_id":3292,"contacts":3293,"url_path":3304},"LLMs in Motion: Transformative Advances in LLMs for Autonomous Navigation and Decision-Making at the Edge","\u003Cp style=\"text-align:justify;\">In emerging applications such as robotics, autonomous vehicles, and smart cities, Large Language Models (LLMs) are increasingly being explored as key components for enabling real-time decision-making in navigation and control tasks. \u003C/p>","\u003Cp style=\"text-align:justify;\">Unlike traditional systems, where processing follows a linear flow from sensing to action, LLMs have the potential to leverage closed-loop frameworks that integrate contextual understanding, planning, and reasoning. These frameworks enable bi-directional information flow, where navigation actions not only depend on sensor inputs but also dynamically adjust sensing strategies based on environmental feedback. This adaptability is crucial for operating in dynamic and resource-constrained environments, where efficiency, robustness, and task-specific optimization are essential. Focusing on these emergent opportunities, this special session highlights advancements in leveraging LLMs for navigation and related applications, demonstrating their transformative potential in real-world scenarios. LLMs address critical challenges such as communication bottlenecks, energy efficiency, and uncertainty quantification, enabling autonomous systems to operate robustly in dynamic and resource-constrained environments. \u003C/p>\u003Cp style=\"text-align:justify;\">For instance, LLM-based compression techniques optimize communication by reducing data transmission overhead while preserving essential task-relevant information, facilitating efficient collaboration among edge agents. In energy-efficient navigation, neuromorphic systems integrate event-driven processing and physics-guided planning to achieve real-time, collision-free operation in complex settings. Such frameworks showcase how advanced sensing and planning methods can significantly enhance autonomous decision-making. Further, computational efficiency improvements, such as adaptive attention mechanisms and mixed precision quantization, enable LLMs to operate effectively on edge hardware, balancing performance with resource constraints. The session also explores risk-aware frameworks, such as conformal prediction, which provide adaptive uncertainty quantification without the need for multiple model passes. These methods empower LLMs to respond flexibly—offering single predictions, sets of possible outcomes, or abstaining based on uncertainty levels—ensuring robust and reliable decision-making. \u003C/p>\u003Cp style=\"text-align:justify;\">Collectively, these advancements illustrate the potential of LLMs to redefine navigation and decision-making in autonomous systems, paving the way for scalable, efficient, and resilient solutions. Key insights in this session are drawn from two DARPA/SRC-funded JUMP 2.0 centers in the United States, CogniSense and CoCoSys, with combined funding of over $60 million USD. CogniSense advances the integration of multispectral sensing with LLM-driven navigation frameworks, while CoCoSys explores distributed cognitive systems for collaborative autonomy. Collaborative activities between these centers further address the broader challenges of optimizing decision-making within individual agents and across networks of autonomous agents. By sharing information and coordinating actions, these systems dynamically adjust resource allocation to meet task requirements while maintaining efficiency and robustness. Through these diverse contributions, this session demonstrates the transformative potential of LLMs to address critical challenges in navigation, edge computing, and collaborative autonomy. By leveraging innovations in compression, energy-efficient processing, and uncertainty quantification, LLMs are poised to drive the next generation of real-time, scalable, and robust autonomous systems in complex and dynamic environments.\u003C/p>","2024-12-13T23:44:57.676Z","2024-12-24T08:15:32.367Z","2024-12-24T08:15:32.363Z","464",[3294,3296],{"id":1068,"name":2194,"committee":16,"position":16,"affiliation":2195,"email":16,"biography":16,"createdAt":2196,"updatedAt":2196,"url_path_id":2197,"contactPhoto":16,"socialLinks":3295,"url_path":2199},[],{"id":3297,"name":3298,"committee":16,"position":16,"affiliation":3299,"email":16,"biography":16,"createdAt":3300,"updatedAt":3300,"url_path_id":3301,"contactPhoto":16,"socialLinks":3302,"url_path":3303},335,"Kaushik Roy","Purdue University","2024-12-13T23:37:58.102Z","386",[],"-182","-260",{"id":617,"session":3306},{"id":582,"title":3307,"teaser":3308,"body":3309,"createdAt":3310,"updatedAt":3311,"publishedAt":3312,"url_path_id":3313,"contacts":3314,"url_path":3323},"Machine Learning and Deep Learning Methods applied to Vision and Robotics (MLDLMVR)","\u003Cp style=\"text-align:justify;\">Over the last decades there has been an increasing interest in using machine learning and in the last few years, deep learning methods, combined with other vision techniques to create autonomous systems that solve vision problems in different fields. This special session is designed to serve researchers and developers to publish original, innovative and state-of-the art algorithms and architectures for real time applications in the areas of computer vision, image processing, biometrics, virtual and augmented reality, neural networks, intelligent interfaces and biomimetic object-vision recognition. \u003C/p>","\u003Cp style=\"text-align:justify;\">This special session provides a platform for academics, developers, and industry-related researchers belonging to the vast communities of *Neural Networks*, *Computational Intelligence*, *Machine Learning*, *Deep Learning*, *Biometrics*, *Vision systems*, and *Robotics *, to discuss, share experience and explore traditional and new areas of the computer vision, machine and deep learning combined to solve a range of problems. The objective of the workshop is to integrate the growing international community of researchers working on the application of Machine Learning and Deep Learning Methods in Vision and Robotics to a fruitful discussion on the evolution and the benefits of this technology to the society.\u003C/p>","2024-12-13T23:44:58.388Z","2024-12-24T08:17:09.009Z","2024-12-24T08:17:09.005Z","465",[3315],{"id":3316,"name":3317,"committee":16,"position":16,"affiliation":3318,"email":16,"biography":16,"createdAt":3319,"updatedAt":3319,"url_path_id":3320,"contactPhoto":16,"socialLinks":3321,"url_path":3322},330,"Jose Garcia-Rodriguez","Universidad de Alicante","2024-12-13T23:37:55.805Z","381",[],"-177","-261",{"id":3325,"session":3326},61,{"id":617,"title":3327,"teaser":3328,"body":3329,"createdAt":3330,"updatedAt":3331,"publishedAt":3332,"url_path_id":3333,"contacts":3334,"url_path":3361},"Machine Learning for Optimisation","\u003Cp style=\"text-align:justify;\">While there has been a lot of research into the use of optimization for improving the performance of machine learning approaches, research into machine learning for optimization is in its infancy. This special session aims to promote research in this area for further advancement of the field. \u003C/p>","\u003Cp style=\"text-align:justify;\">The special session focuses on using reinforcement learning, supervised learning, unsupervised learning, and recent advancements in the field, such as Large Language Models (LLMs) and generative artificial intelligence, in optimization techniques, such as evolutionary algorithms, to improve the performance of optimization approaches. To the organizers’ knowledge, this is the first time that such a topic has been proposed for a special session would be part of the IJCNN program. Flagship conferences in evolutionary computation, e.g., GECCO and CEC, have introduced similar sessions over the past two years. However, the IJCNN program has yet to include it, and it is crucial to obtain perspectives from researchers working in machine learning to advance this area further.\u003C/p>","2024-12-13T23:44:59.139Z","2024-12-24T08:18:45.556Z","2024-12-24T08:18:45.552Z","466",[3335,3343,3351,3353],{"id":3336,"name":3337,"committee":16,"position":16,"affiliation":3338,"email":16,"biography":63,"createdAt":3339,"updatedAt":3339,"url_path_id":3340,"contactPhoto":16,"socialLinks":3341,"url_path":3342},433,"Nelishia Pillay","University of Pretoria","2024-12-24T08:18:27.580Z","554",[],"-349",{"id":3344,"name":3345,"committee":16,"position":16,"affiliation":3346,"email":16,"biography":16,"createdAt":3347,"updatedAt":3347,"url_path_id":3348,"contactPhoto":16,"socialLinks":3349,"url_path":3350},329,"Jorge Cruz-Duarte","Tecnológico de Monterrey","2024-12-13T23:37:55.325Z","380",[],"-176",{"id":2341,"name":2342,"committee":16,"position":16,"affiliation":2316,"email":16,"biography":16,"createdAt":2343,"updatedAt":2343,"url_path_id":2344,"contactPhoto":16,"socialLinks":3352,"url_path":2346},[],{"id":3354,"name":3355,"committee":16,"position":16,"affiliation":3356,"email":16,"biography":16,"createdAt":3357,"updatedAt":3357,"url_path_id":3358,"contactPhoto":16,"socialLinks":3359,"url_path":3360},299,"Geoff Nitschke","University of Cape Town","2024-12-13T23:37:42.509Z","350",[],"-146","-262",{"id":168,"session":3363},{"id":3325,"title":3364,"teaser":3365,"body":3366,"createdAt":3367,"updatedAt":3368,"publishedAt":3369,"url_path_id":3370,"contacts":3371,"url_path":3393},"Machine Learning in Complex Energy Systems and Future Sustainability","\u003Cp style=\"text-align:justify;\">The recent trends in energy systems evolution towards to sustainable production and use of energy employ information, communication, and automation technology to deploy an integrated power system with sustainability challenges in the complete value chain, from power generation, to transmission, distribution, final users and stakeholders. \u003C/p>","\u003Cp>The traditional smart grid paradigm combined with higher penetration of e-mobility and increasing role of electric storage, both at residential and utility scale, is aligned with the policy goals of expanding the application of renewable energy, energy conservation and carbon reduction. \u003C/p>\u003Cp>Renewable energy sources in the last decade got more attention due to cost competitiveness and environmental sustainability, as compared to fossil fuel and nuclear power generations. Owing to the relatively lower capacity factors of renewable power generation systems, it is important to operate the systems near their maximum power output point, especially for the wind and solar PV generation systems. In addition, due to intrinsic intermittency, the role of battery energy storage systems is increasing at multiple scales, requiring more accurate predictions and modeling not only to enable demand side management services, but also to track their efficiency during the lifetime and assure reliable ancillary services for large utility scale plants. The future energy system is a complex field of study for automation, safety, data analysis and the close cooperation between the users and suppliers can improve the operating efficiency of the system itself, to enhance power quality and to solidify grid reliability. Moreover, power grid integrated with smart meters, EV charging stations and home (building) energy management system are the key enabling factor toward the Smart City concept when the principal context is the urban scenario. Moreover, due to the major role of electric vector to allow the decarbonization process and meet high sustainability goals, it is no more conceivable as a mere commodity, and the price of electricity will represent a crucial topic as a social primary good again impacting on sustainability. \u003C/p>\u003Cp>Energy communities and trading markets represent two completely different application fields where the same technological advancements have opposite impacts underlying the inner complexity of the evolving energy system, due to coexistence of physical and digital layers. As a result, modeling and controlling the energy system using advanced techniques, such as pervasive electronic devices, smart meters, micro-grids, control algorithms and distributed automations become crucial issues. Additionally, effective uses of computational intelligence techniques such as neural networks, machine learning, reinforcement and deep learning for the controlling and modeling of different components and processes in energy systems turn out to be fundamental for successful operations of the systems. The main aim of this session is to provide a forum for researchers covering the whole range of neural networks and machine learning applications to energy systems and developing sustainable solutions.\u003C/p>","2024-12-13T23:44:59.929Z","2024-12-24T08:20:11.289Z","2024-12-24T08:20:11.284Z","467",[3372,3380,3386],{"id":3373,"name":3374,"committee":16,"position":16,"affiliation":3375,"email":16,"biography":16,"createdAt":3376,"updatedAt":3376,"url_path_id":3377,"contactPhoto":16,"socialLinks":3378,"url_path":3379},291,"Francesco Grimaccia","Politecnico di Milano","2024-12-13T23:37:39.661Z","342",[],"-138",{"id":1106,"name":3381,"committee":16,"position":16,"affiliation":3375,"email":16,"biography":16,"createdAt":3382,"updatedAt":3382,"url_path_id":3383,"contactPhoto":16,"socialLinks":3384,"url_path":3385},"Marco Mussetta","2024-12-13T23:38:10.989Z","408",[],"-204",{"id":3387,"name":3388,"committee":16,"position":16,"affiliation":3375,"email":16,"biography":16,"createdAt":3389,"updatedAt":3389,"url_path_id":3390,"contactPhoto":16,"socialLinks":3391,"url_path":3392},227,"Alessandro Niccolia","2024-12-13T23:37:20.244Z","278",[],"-74","-263",{"id":31,"session":3395},{"id":168,"title":3396,"teaser":3397,"body":3398,"createdAt":3399,"updatedAt":3400,"publishedAt":3401,"url_path_id":3402,"contacts":3403,"url_path":3433},"Multimodal Deep Learning in Applications","\u003Cp style=\"text-align:justify;\">Multimodal deep learning is a dynamic and innovative research area in a neural network. It focuses on developing sophisticated models with new types of architectures and mechanisms. These models enable the creation of intelligent systems capable of extracting knowledge from different types of data leading to groundbreaking advancements in neural networks.\u003C/p>","\u003Cp style=\"text-align:justify;\">In particular, multimodal models based on neural networks enable a better understanding of the context by analyzing data from various sources or solving much more complex problems. This is important due to the possibility of using these solutions in practical applications of the Internet of Things. The most important aspects analyzed in this special session are graph/convolutional neural networks, hybrid solutions, multicriteria decision problems, and federated learning. The purpose of this special session is to encourage research and innovation in the fields of multimodal deep learning in applications. We are looking for ideas that focus on the use and implications of multimodal deep learning for transforming the manner in which applications operate.\u003C/p>","2024-12-13T23:45:00.822Z","2024-12-24T08:21:24.227Z","2024-12-24T08:21:24.222Z","468",[3404,3411,3419,3426],{"id":3405,"name":3406,"committee":16,"position":16,"affiliation":1357,"email":16,"biography":16,"createdAt":3407,"updatedAt":3407,"url_path_id":3408,"contactPhoto":16,"socialLinks":3409,"url_path":3410},314,"Houbing Song","2024-12-13T23:37:48.607Z","365",[],"-161",{"id":3412,"name":3413,"committee":16,"position":16,"affiliation":3414,"email":16,"biography":16,"createdAt":3415,"updatedAt":3415,"url_path_id":3416,"contactPhoto":16,"socialLinks":3417,"url_path":3418},298,"Gautam Srivastava","Brandon University","2024-12-13T23:37:42.150Z","349",[],"-145",{"id":3420,"name":3421,"committee":16,"position":16,"affiliation":1253,"email":16,"biography":16,"createdAt":3422,"updatedAt":3422,"url_path_id":3423,"contactPhoto":16,"socialLinks":3424,"url_path":3425},336,"Keping Yu","2024-12-13T23:37:58.579Z","387",[],"-183",{"id":3427,"name":3428,"committee":16,"position":16,"affiliation":2222,"email":16,"biography":16,"createdAt":3429,"updatedAt":3429,"url_path_id":3430,"contactPhoto":16,"socialLinks":3431,"url_path":3432},265,"Dawid Polap","2024-12-13T23:37:31.231Z","316",[],"-112","-264",{"id":3435,"session":3436},64,{"id":31,"title":3437,"teaser":3438,"body":3439,"createdAt":3440,"updatedAt":3441,"publishedAt":3442,"url_path_id":3443,"contacts":3444,"url_path":3468},"Neural Architecture Search's Theory, Algorithm and Application","\u003Cp style=\"text-align:justify;\">Deep neural networks have demonstrated substantial promise in a wide range of real-world applications, primarily due to their intricate architectures developed by domain experts. However, the architectural design process is often labor-intensive, which has imposed significant constraints on the further advancement of deep neural networks. \u003C/p>","\u003Cp style=\"text-align:justify;\">These challenges have led to the rise of Neural Architecture Search (NAS). NAS-designed architectures have recently exhibited superior performance in many tasks compared to manually designed counterparts, gaining considerable traction in the deep learning field. Specifically, NAS begins by defining a search space that encompasses all potential architectures. It then employs a well-crafted search strategy to identify the optimal architecture. \u003C/p>\u003Cp style=\"text-align:justify;\">Throughout the search process, NAS must evaluate the performance of each explored architecture to guide the search strategy effectively. The NAS problem is inherently challenging due to the presence of multiple issues, such as complex constraints, discrete representations, bi-level structures, computational expense, and conflicting objectives. Recently, various methods for NAS have been introduced to address these challenges. \u003C/p>\u003Cp style=\"text-align:justify;\">From an optimization perspective, multi-objective, many-objective, multimodal, and multi-task optimization approaches have been proposed to solve NAS problems. To improve search efficiency, researchers have developed weight inheritance, performance predictors, zero-shot approaches, and other techniques. Moreover, NAS-based approaches have emerged in novel neural networks and various practical applications. Despite the demonstrated efficacy of existing NAS methods, unresolved challenges and unexplored directions remain, such as uniform representation, cross-domain prediction, and reliable benchmarks.\u003C/p>","2024-12-13T23:45:01.749Z","2024-12-24T08:23:16.368Z","2024-12-24T08:23:16.357Z","469",[3445,3453,3460],{"id":3446,"name":3447,"committee":16,"position":16,"affiliation":3448,"email":16,"biography":16,"createdAt":3449,"updatedAt":3449,"url_path_id":3450,"contactPhoto":16,"socialLinks":3451,"url_path":3452},344,"Lianbo Ma","Northeastern University","2024-12-13T23:38:03.145Z","395",[],"-191",{"id":3454,"name":3455,"committee":16,"position":16,"affiliation":3448,"email":16,"biography":63,"createdAt":3456,"updatedAt":3456,"url_path_id":3457,"contactPhoto":16,"socialLinks":3458,"url_path":3459},435,"Nan Li","2024-12-24T08:23:03.535Z","556",[],"-351",{"id":3461,"name":3462,"committee":16,"position":16,"affiliation":3463,"email":16,"biography":63,"createdAt":3464,"updatedAt":3464,"url_path_id":3465,"contactPhoto":16,"socialLinks":3466,"url_path":3467},434,"Yan Pei","University of Aizu","2024-12-24T08:22:51.705Z","555",[],"-350","-265",{"id":3470,"session":3471},65,{"id":3435,"title":3472,"teaser":3473,"body":3474,"createdAt":3475,"updatedAt":3476,"publishedAt":3477,"url_path_id":3478,"contacts":3479,"url_path":3493},"Neural methods for IR and RecSys","\u003Cp style=\"text-align:justify;\">The landscape of information retrieval (IR) and recommender systems (RecSys) has been fundamentally reshaped by advances in neural methods.Leveraging deep learning, transformational architectures, and advanced neural embeddings, the IR and RecSys fields are witnessing rapid innovations that enable more personalised, context-aware, and accurate recommendations and retrieval results.\u003C/p>","\u003Cp style=\"text-align:justify;\">This special session aims to provide a platform for leading researchers to share new insights into the application of neural methods in IR and RecSys, and to foster discussions on recent advances and unexplored areas of research. In recent years, IR and RecSys have seen remarkable growth in their reliance on neural architectures. These methods can significantly improve the understanding of complex user needs and dynamic data more effectively than traditional methods. However, this adoption also brings new challenges, including scalability issues and the need for explainability. The aim of this session is to bring together experts from the neural, IR and RecSys communities to address these emerging challenges and opportunities.\u003C/p>","2024-12-13T23:45:03.371Z","2025-05-13T14:22:50.110Z","2024-12-24T08:24:30.846Z","470",[3480,3487],{"id":3481,"name":3482,"committee":16,"position":16,"affiliation":1522,"email":16,"biography":16,"createdAt":3483,"updatedAt":3483,"url_path_id":3484,"contactPhoto":16,"socialLinks":3485,"url_path":3486},283,"Federico Siciliano","2024-12-13T23:37:36.974Z","334",[],"-130",{"id":600,"name":3488,"committee":16,"position":16,"affiliation":1900,"email":16,"biography":63,"createdAt":3489,"updatedAt":3489,"url_path_id":3490,"contactPhoto":16,"socialLinks":3491,"url_path":3492},"Giulia Di Teodoro","2024-12-10T18:00:54.689Z","106",[],"-63","-266",{"id":3495,"session":3496},66,{"id":3470,"title":3497,"teaser":3498,"body":3499,"createdAt":3500,"updatedAt":3501,"publishedAt":3502,"url_path_id":3503,"contacts":3504,"url_path":3521},"Neural networks for nondestructive evaluation and structural health monitoring","\u003Cp style=\"text-align:justify;\">Data-driven models and Machine Learning (ML) methods can unleash the full potential of nondestructive evaluation (NDE) and structural health monitoring (SHM), making them key technologies for achieving various objectives of industry 4.0 and 5.0. Machine learning can improve the efficiency of the classification of NDE data, which is still frequently done by trained operators, by supporting their decisions, or replacing them in some applications facilitating automation of nondestructive evaluation analysis. \u003C/p>","\u003Cp style=\"text-align:justify;\">Starting with IoT and Industry 4.0 paradigms, NDE methods have been increasingly integrated in manufacturing processes as well as in agriculture to monitor the quality of the production with the aim of reducing waste while assuring quality. Increasing the reliability of autonomous decision is of utter importance in these applications. NDE and SHM analysis is also crucial for ensuring safety of civil structures, transportation, energy production and distribution, etc. \u003C/p>\u003Cp style=\"text-align:justify;\">By processing historical noisy data by means of ML methods can significantly increase sensitivity and accuracy of the evaluation. Furthermore, data-driven digital twins can be implemented to improve monitoring, diagnostics, and prognostics, leading to an improved safety. But that is not all: deep learning algorithms can process and consider the full information enclosed in NDE and SHM data and reveal hidden correlations and extract features which cannot be evident even to experts, paving the way for new evaluation methods, classification capability and applications. \u003C/p>\u003Cp style=\"text-align:justify;\">This is the case of convolutional neural networks that have been applied in recent years for the denoising of ultrasonic and thermography signals and images to improve defect detection and in many other NDE/SHM applications, including in the field of cultural heritage diagnostics both for defect detection and for material mappings. There is therefore great room for improvement, and the objective of this session is twofold: creating a community of researchers aimed at integrating machine learning in NDE and SHM which can share methods, data, models, and foster the collaboration between NDE/SHM researchers and neural networks experts to find new solutions to tackle open challenges.\u003C/p>","2024-12-13T23:45:04.919Z","2024-12-24T08:26:22.100Z","2024-12-24T08:26:22.096Z","471",[3505,3513],{"id":3506,"name":3507,"committee":16,"position":16,"affiliation":3508,"email":16,"biography":16,"createdAt":3509,"updatedAt":3509,"url_path_id":3510,"contactPhoto":16,"socialLinks":3511,"url_path":3512},358,"Marco Ricci","Università della Calabria","2024-12-13T23:38:11.521Z","409",[],"-205",{"id":3514,"name":3515,"committee":16,"position":16,"affiliation":3516,"email":16,"biography":63,"createdAt":3517,"updatedAt":3517,"url_path_id":3518,"contactPhoto":16,"socialLinks":3519,"url_path":3520},436,"Xiaokang Yin","China University of Petroleum (East China)","2024-12-24T08:26:10.982Z","557",[],"-352","-267",{"id":742,"session":3523},{"id":3495,"title":3524,"teaser":3525,"body":3526,"createdAt":3527,"updatedAt":3528,"publishedAt":3529,"url_path_id":3530,"contacts":3531,"url_path":3569},"NeuroCAS: Neuromorphic Computing for Intelligent Autonomous Systems","\u003Cp style=\"text-align:justify;\">This special session aims to bring together researchers and practitioners in the fields of neuromorphic computing, spiking neural networks, and autonomous systems (e.g., robotics). With the growing demand for intelligent, adaptive, and efficient autonomous systems across various application use-cases such as robotics, mobile agents (e.g., UAVs), and self-driving vehicles, neuromorphic computing offers a bio-inspired approach to enable these systems with embodied intelligence. \u003C/p>","\u003Cp style=\"text-align:justify;\">This session will explore the latest advances in neuromorphic algorithms, hardware platforms, cross-layer optimizations, and their applications in real-world autonomous systems, with particular attention to event-based dynamic vision sensing and multi-modality sensing for enhanced perception and responsiveness. \u003C/p>\u003Cp style=\"text-align:justify;\">This session will particularly emphasize novel neuromorphic approaches for energy efficiency, adaptability, and reliability, that highlight the intersection of spiking neural networks and autonomous systems. Insights will be drawn from recent research and developments, including perspectives from the communities of machine learning, spiking neural networks, autonomous systems, robotics, and neuroscience. Researchers will discuss the potential of neuromorphic computing to address challenges such as real-time decision-making, continual learning, as well as secure and robust autonomous systems.\u003C/p>","2024-12-13T23:45:06.655Z","2024-12-24T08:28:47.600Z","2024-12-24T08:28:47.596Z","472",[3532,3540,3547,3554,3562],{"id":3533,"name":3534,"committee":16,"position":16,"affiliation":3535,"email":16,"biography":16,"createdAt":3536,"updatedAt":3536,"url_path_id":3537,"contactPhoto":16,"socialLinks":3538,"url_path":3539},224,"Alberto Marchisio","New York University Abu Dhabi","2024-12-13T23:37:19.479Z","275",[],"-71",{"id":3541,"name":3542,"committee":16,"position":16,"affiliation":3535,"email":16,"biography":63,"createdAt":3543,"updatedAt":3543,"url_path_id":3544,"contactPhoto":16,"socialLinks":3545,"url_path":3546},437,"Muhammad Shafique","2024-12-24T08:28:09.270Z","558",[],"-353",{"id":3548,"name":3549,"committee":16,"position":16,"affiliation":1280,"email":16,"biography":63,"createdAt":3550,"updatedAt":3550,"url_path_id":3551,"contactPhoto":16,"socialLinks":3552,"url_path":3553},438,"Maurizio Martina","2024-12-24T08:28:25.101Z","559",[],"-354",{"id":3555,"name":3556,"committee":16,"position":16,"affiliation":3557,"email":16,"biography":16,"createdAt":3558,"updatedAt":3558,"url_path_id":3559,"contactPhoto":16,"socialLinks":3560,"url_path":3561},307,"Hadjer Benmeziane","IBM","2024-12-13T23:37:45.591Z","358",[],"-154",{"id":38,"name":3563,"committee":16,"position":16,"affiliation":3564,"email":16,"biography":16,"createdAt":3565,"updatedAt":3565,"url_path_id":3566,"contactPhoto":16,"socialLinks":3567,"url_path":3568},"Arnab Raha","Intel Corporation","2024-12-13T23:37:25.283Z","296",[],"-92","-268",{"id":761,"session":3571},{"id":742,"title":3572,"teaser":3573,"body":3574,"createdAt":3575,"updatedAt":3576,"publishedAt":3577,"url_path_id":3578,"contacts":3579,"url_path":3608},"Privacy-Preserving Human Pose Estimation","\u003Cp style=\"text-align:justify;\">Human Pose Estimation (HPE) has rapidly become a cornerstone of AI-driven computer vision, employing advanced neural networks to interpret human postures and movements from visual or sensor data. HPE is a key technology in healthcare, security, sports analytics, workplace ergonomics, and human-computer interaction applications. \u003C/p>","\u003Cp style=\"text-align:justify;\">However, as neural network-based HPE systems become widely adopted, significant privacy challenges arise due to the processing of sensitive biometric data, including facial features and body shape. The demand for privacy preserving HPE is driven by stringent data protection regulations such as the European Union's General Data Protection Regulation (GDPR), the European AI Act, and the California Consumer Privacy Act (CCPA), which mandate stricter guidelines on data handling. \u003C/p>\u003Cp style=\"text-align:justify;\">Privacy issues are compulsory when neural network models require continuous data monitoring, external server processing, or long-term storage, especially in high-resolution applications that may reveal personally identifiable information (PII). This special session addresses the need for innovative neural networks that enhance HPE while embedding robust privacy-preserving mechanisms. \u003C/p>\u003Cp style=\"text-align:justify;\">It seeks to gather researchers and practitioners to discuss new models, frameworks, and methodologies that balance privacy and performance. Emerging neural network approaches, including privacy-aware architectures, differential privacy, secure multi-party computation, and federated learning, offer promising solutions for HPE without compromising data privacy. Also, alternative input modalities, such as depth, thermal, radiofrequency data, and skeleton-only models, inherently reduce the exposure of PII compared to traditional RGB inputs, adhering to the principles of privacy by design. Despite advancements in HPE, the integration of privacy-preserving measures within neural network architectures still needs to be explored, presenting a novel research frontier. \u003C/p>\u003Cp style=\"text-align:justify;\">This special session aligns directly with the objectives of IJCNN 2025, emphasizing the development of advanced neural network methodologies and responsible AI applications. By creating a platform focused on the intersection of HPE and privacy, this session aims to drive impactful research, foster cross-disciplinary collaboration, and establish new benchmarks for privacyaware neural network design. We invite submissions of original research that contribute to state-of-the-art neural network solutions for privacy-preserving HPE.\u003C/p>","2024-12-13T23:45:07.985Z","2024-12-24T08:31:00.339Z","2024-12-24T08:31:00.335Z","473",[3580,3587,3594,3601],{"id":3581,"name":3582,"committee":16,"position":16,"affiliation":1900,"email":16,"biography":16,"createdAt":3583,"updatedAt":3583,"url_path_id":3584,"contactPhoto":16,"socialLinks":3585,"url_path":3586},295,"Francesco Pistolesi","2024-12-13T23:37:41.075Z","346",[],"-142",{"id":3588,"name":3589,"committee":16,"position":16,"affiliation":1900,"email":16,"biography":63,"createdAt":3590,"updatedAt":3590,"url_path_id":3591,"contactPhoto":16,"socialLinks":3592,"url_path":3593},439,"Michele Baldassini","2024-12-24T08:30:26.883Z","560",[],"-355",{"id":3595,"name":3596,"committee":16,"position":16,"affiliation":1900,"email":16,"biography":63,"createdAt":3597,"updatedAt":3597,"url_path_id":3598,"contactPhoto":16,"socialLinks":3599,"url_path":3600},440,"Matteo Mugnai","2024-12-24T08:30:41.188Z","561",[],"-356",{"id":3602,"name":3603,"committee":16,"position":16,"affiliation":1900,"email":16,"biography":16,"createdAt":3604,"updatedAt":3604,"url_path_id":3605,"contactPhoto":16,"socialLinks":3606,"url_path":3607},250,"Beatrice Lazzerini","2024-12-13T23:37:26.690Z","301",[],"-97","-269",{"id":851,"session":3610},{"id":761,"title":3611,"teaser":3612,"body":3613,"createdAt":3614,"updatedAt":3615,"publishedAt":3616,"url_path_id":3617,"contacts":3618,"url_path":3633},"Privacy-Preserving Machine and Deep Learning","\u003Cp style=\"text-align:justify;\">Privacy-Preserving Machine and Deep Learning (PP-MDL) is an emerging research area focused on enabling inference and training of Machine and Deep Learning (ML and DL) models in ways that protect the privacy of user data, often originating from as-a-service platforms. This interdisciplinary field spans Artificial Intelligence (AI), statistical methods (such as Differential Privacy (DP) and k-Anonymity), and cryptographic techniques (such as Homomorphic Encryption (HE) and Multi-Party Computation (MPC)). \u003C/p>","\u003Cp style=\"text-align:justify;\">Moreover, entirely new AI paradigms, such as Federated Learning (FL), have emerged specifically to address privacy concerns. The integration of these tools, and particularly the intersection of their applications, promises to drive the next generation of PP-MDL, which is anticipated to become the standard in the coming years. Despite recent exponential growth in PP-MDL literature, a single, definitive solution remains elusive, as each technique has distinct advantages and limitations. These challenges are actively addressed by the PP-MDL community, leveraging expertise from AI, statistics, cryptography, and computational intelligence. Overcoming these challenges is essential for advancing PP-MDL, enabling broader adoption and fostering more powerful, privacy-aware, and secure AI solutions, thereby meeting the increasing demands from users, providers, and regulatory bodies. This Special Session aims to bring together innovative contributions that can drive the development of more effective and efficient PP-MDL solutions. The diversity of attendees at IJCNN presents a unique opportunity to broaden the impact of this field, welcoming fresh perspectives and exploring new research directions, application scenarios, and interdisciplinary contributions.\u003C/p>","2024-12-13T23:45:09.058Z","2024-12-24T08:40:13.453Z","2024-12-24T08:33:16.882Z","474",[3619,3626],{"id":3620,"name":3621,"committee":16,"position":16,"affiliation":3375,"email":16,"biography":16,"createdAt":3622,"updatedAt":3622,"url_path_id":3623,"contactPhoto":16,"socialLinks":3624,"url_path":3625},353,"Manuel Roveri","2024-12-13T23:38:08.332Z","404",[],"-200",{"id":3627,"name":3628,"committee":16,"position":16,"affiliation":3375,"email":16,"biography":16,"createdAt":3629,"updatedAt":3629,"url_path_id":3630,"contactPhoto":16,"socialLinks":3631,"url_path":3632},226,"Alessandro Falcetta","2024-12-13T23:37:19.982Z","277",[],"-73","-270",{"id":141,"session":3635},{"id":141,"title":3636,"teaser":3637,"body":3638,"createdAt":3639,"updatedAt":3640,"publishedAt":3641,"url_path_id":3642,"contacts":3643,"url_path":3652},"Quantum Machine Learning Algorithms and Applications","\u003Cp style=\"text-align:justify;\">In recent years, quantum computing has witnessed significant advancements, evolving from its conceptual foundations in the 1980s to the development of hardware prototypes in the 2020s capable of operating with hundreds of qubits. Despite its early-stage maturity, rapid progress in quantum hardware and algorithm development has ignited discussions on the potential computational supremacy of Noisy Intermediate-Scale Quantum (NISQ) devices over classical systems. \u003C/p>","\u003Cp style=\"text-align:justify;\">Among the diverse algorithms designed for NISQ platforms, the Variational Quantum Eigensolver (VQE) emerges as particularly promising. It demonstrates the capability to operate efficiently with a constrained number of qubits while exhibiting robust resilience to noise. Furthermore, theoretical and empirical studies underscore the potential quantum advantage offered by such algorithms. Classified as hybrid quantum-classical methodologies, Variational Quantum Eigensolver (VQE) algorithms enable the practical application of Variational Quantum Circuits (VQCs), effectively integrating classical machine learning and artificial intelligence frameworks. \u003C/p>\u003Cp style=\"text-align:justify;\">A notable feature of VQCs is their adaptability in constructing Quantum Neural Networks (QNNs), which have demonstrated success across diverse applications. These include quantum convolutional neural networks (QCNNs) for image classification, quantum generative adversarial networks (QGANs) for image reconstruction, quantum long short-term memory (QLSTM) models for time-series modeling, financial forecasting, and natural language processing, as well as quantum reinforcement learning (QRL) for complex sequential decision-making tasks. These methodologies provide a comprehensive framework that leverages the complementary strengths of quantum and classical computation. Furthermore, the capabilities of QNNs have been extensively studied in areas such as model compression and efficient neural network learning. \u003C/p>\u003Cp style=\"text-align:justify;\">By exploiting the exponential nature of quantum systems, where $n$ qubits can represent $2^n$ classical neural network weights and biases, quantum-enhanced neural network training has been applied to tasks such as classification, sequential learning, reinforcement learning, and privacy-preserving approaches like federated learning. QNNs have demonstrated their potential not only as standalone machine learning models but also as tools to enhance the performance of existing classical neural network architectures. In this context, our proposal seeks to undertake a comprehensive exploration of Variational Quantum Circuit (VQC)-based Quantum Machine Learning (QML) algorithms, advancing the frontiers of state-of-the-art QML while examining their applications across diverse machine learning and artificial intelligence challenges. This session will specifically delve into the potential of quantum-enhanced agents and multi-agent systems to learn and adapt within cooperative environments. \u003C/p>\u003Cp style=\"text-align:justify;\">Such advancements hold the promise of transforming fields such as autonomous systems, smart grids, and decentralized AI systems. This special session welcomes submissions across a diverse range of QML topics, including foundational training algorithms, trustworthy and privacy-preserving QML techniques, multi-agent learning frameworks, generative AI enhanced by quantum methodologies, and a wide array of application scenarios. Submissions may address challenges and innovations in scientific discovery as well as commercial and industrial applications, emphasizing the transformative potential of QML in real-world contexts.\u003C/p>","2024-12-13T23:45:10.166Z","2024-12-24T08:32:36.119Z","2024-12-24T08:32:36.115Z","475",[3644],{"id":3645,"name":3646,"committee":16,"position":16,"affiliation":3647,"email":16,"biography":63,"createdAt":3648,"updatedAt":3648,"url_path_id":3649,"contactPhoto":16,"socialLinks":3650,"url_path":3651},441,"Samuel Yen-Chi Chen","Wells Fargo","2024-12-24T08:32:25.596Z","562",[],"-357","-271",{"id":3654,"session":3655},70,{"id":3654,"title":3656,"teaser":3657,"body":3658,"createdAt":3659,"updatedAt":3660,"publishedAt":3661,"url_path_id":3662,"contacts":3663,"url_path":3680},"Randomization Based Deep and Shallow Learning Methods and Applications to Healthcare Domain","\u003Cp style=\"text-align:justify;\">Randomization-based learning algorithms have received considerable attention from academics, researchers, and domain workers because randomization-based neural networks can be trained by non-iterative approaches possessing closed-form solutions. Those methods are generally computationally faster than iterative solutions and less sensitive to parameter settings. \u003C/p>","\u003Cp style=\"text-align:justify;\">Even though randomization-based non-iterative methods have attracted much attention in recent years, their deep structures have not been sufficiently developed nor benchmarked. This special session aims to bridge this gap. The first target of this special session is to present the recent advances in randomization- based learning methods. Randomization-based neural networks usually offer non-iterative closed-form solutions. Secondly, the focus is on promoting the concepts of non-iterative optimization with respect to counterparts, such as gradient-based methods and derivative-free iterative optimization techniques. \u003C/p>\u003Cp style=\"text-align:justify;\">Besides the dissemination of the latest research results on randomization-based and/or non-iterative algorithms, it is also expected that this special session will cover some practical applications, present some new ideas and identify directions for future studies. Original contributions as well as comparative studies among randomization-based and non-randomized-based methods are welcome with unbiased literature review and comparative studies. Original contributions having biomedical applications with or without randomization algorithms are also welcome. \u003C/p>\u003Cp style=\"text-align:justify;\">Typical deep/shallow paradigms include (but not limited to) random vector functional link (RVFL), randomized recurrent networks (RRN), kernel ridge regression (KRR) with randomization, extreme learning machines (ELM), random forests (RF), stochastic configuration network (SCN), broad learning system (BLS), convolution neural networks (CNN) with randomization, and so on.\u003C/p>","2024-12-13T23:45:11.122Z","2024-12-24T08:34:31.306Z","2024-12-24T08:34:31.301Z","476",[3664,3672],{"id":3665,"name":3666,"committee":16,"position":16,"affiliation":3667,"email":16,"biography":63,"createdAt":3668,"updatedAt":3668,"url_path_id":3669,"contactPhoto":16,"socialLinks":3670,"url_path":3671},442,"Ponnuthurai Suganthan","Qatar University","2024-12-24T08:34:20.536Z","563",[],"-358",{"id":3673,"name":3674,"committee":16,"position":16,"affiliation":3675,"email":16,"biography":16,"createdAt":3676,"updatedAt":3676,"url_path_id":3677,"contactPhoto":16,"socialLinks":3678,"url_path":3679},351,"M Tanveer","IIT Indore","2024-12-13T23:38:07.245Z","402",[],"-198","-272",{"id":3682,"session":3683},73,{"id":122,"title":3684,"teaser":3685,"body":3686,"createdAt":3687,"updatedAt":3688,"publishedAt":3689,"url_path_id":3690,"contacts":3691,"url_path":3708},"Recent Trends in Communication and Data Analyzing Techniques for IoT (RTCDATI)","\u003Cp style=\"text-align:justify;\">Over the past decade, the Internet of Things (IoT) has become one of the most influential technologies in the fields of wireless communications and mobile computing. Originated from RFID and wireless sensor networks (WSNs), the paradigm of IoT has been transforming every aspect of human life including healthcare, energy, transportation, and manufacturing. \u003C/p>","\u003Cp style=\"text-align:justify;\">Recent predictions show that there will be more than 20 billion IoT devices by 2020. Since its very beginning, wireless communication has been focused on serving human-to-human interaction or human accessing information. Due to IoT, the scope of wireless communication becomes ubiquitous communication among all people and all devices, and the major challenge now becomes how to realize large-scale device-to-device (D2D) communication in an intelligent and energy efficient fashion. On the other hand, mobile computing is expected to be more pervasive and resource constrained than any time before. To facilitate IoT, there are tremendous innovation opportunities in different disciplines and perspectives. This session is seeking high-quality research articles as well as reviews about state-of-the-art technologies in wireless communications and mobile computing that contribute to the formation and advancement of IoT. Since power and cost constraints are major factors of IoT development, they will be the focus of this special issue.\u003C/p>","2024-12-24T08:43:08.355Z","2024-12-24T08:43:10.593Z","2024-12-24T08:43:10.589Z","569",[3692,3700],{"id":3693,"name":3694,"committee":16,"position":16,"affiliation":3695,"email":16,"biography":63,"createdAt":3696,"updatedAt":3696,"url_path_id":3697,"contactPhoto":16,"socialLinks":3698,"url_path":3699},444,"Rohit Tanwar","University of Petroleum and Energy Studies, Dehradun","2024-12-24T08:42:32.781Z","567",[],"-362",{"id":3701,"name":3702,"committee":16,"position":16,"affiliation":3703,"email":16,"biography":63,"createdAt":3704,"updatedAt":3704,"url_path_id":3705,"contactPhoto":16,"socialLinks":3706,"url_path":3707},445,"Sonali Vyas","UPES University Dehradun","2024-12-24T08:42:49.633Z","568",[],"-363","-364",{"id":122,"session":3710},{"id":780,"title":3711,"teaser":3712,"body":3713,"createdAt":3714,"updatedAt":3715,"publishedAt":3716,"url_path_id":3717,"contacts":3718,"url_path":3757},"Reservoir computing in the deep learning era: theory, models, applications, and hardware implementations","\u003Cp>Reservoir Computing (RC) has emerged as a computationally efficient approach to training recurrent neural networks (RNNs), offering unique capabilities in handling temporal data without the high resource demands of traditional deep learning models. With the increasing need for low-power, fast, and adaptable neural networks across domains like real-time signal processing, edge computing, and neuromorphic systems, RC presents a compelling solution. \u003C/p>","\u003Cp>Yet, as deep learning methods evolve, RC faces critical challenges that call for new theoretical insights, model innovations, and hardware implementations. Specifically, RC must address limitations in scalability, robustness, and adaptability to maintain its relevance alongside modern neural architectures. This special session aims to advance Reservoir Computing (RC) by tackling key challenges that span theoretical, model, application, and hardware dimensions. A primary goal is to expand RC’s theoretical foundations to enhance stability and adaptability, especially in dynamic environments, drawing on insights from dynamical systems and control theory to make RC more robust and reliable in real-world applications. \u003C/p>\u003Cp>The session also seeks to explore hybrid architectures that combine RC with deep learningapproaches, such as graph-based and hierarchical models, enabling RC to scale and handle complex, high-dimensional spatiotemporal tasks, including video and text analysis. Another objective is to foster innovative applications in fields requiring efficient, low-latency data processing, such as robotics, neuroscience, and IoT, where RC’s computational efficiency proves advantageous for real-time and resource-constrained contexts. Moreover, the session promotes advances in hardware implementations to enable energyefficient AI, supporting RC’s deployment on neuromorphic platforms like electronic, photonic, spintronic, and biological substrates. \u003C/p>\u003Cp style=\"text-align:justify;\">This direction highlights RC’s potential for ultra-fast and/or low-energy applications critical to embedded systems and edge AI. Finally, the session aims to foster interdisciplinary collaboration by joining insights from machine learning, physics, neuroscience, and hardware engineering. This collaborative approach willdrive innovation, positioning RC as a foundational framework within modern AI that addresses both theoretical challenges and practical needs across various domains.\u003C/p>","2024-12-24T08:50:41.396Z","2024-12-24T08:50:44.663Z","2024-12-24T08:50:44.659Z","579",[3719,3726,3733,3741,3749],{"id":3720,"name":3721,"committee":16,"position":16,"affiliation":1900,"email":16,"biography":16,"createdAt":3722,"updatedAt":3722,"url_path_id":3723,"contactPhoto":16,"socialLinks":3724,"url_path":3725},260,"Claudio Gallicchio","2024-12-13T23:37:29.631Z","311",[],"-107",{"id":3727,"name":3728,"committee":16,"position":16,"affiliation":1900,"email":16,"biography":16,"createdAt":3729,"updatedAt":3729,"url_path_id":3730,"contactPhoto":16,"socialLinks":3731,"url_path":3732},237,"Andrea Ceni","2024-12-13T23:37:22.861Z","288",[],"-84",{"id":3734,"name":3735,"committee":16,"position":16,"affiliation":3736,"email":16,"biography":16,"createdAt":3737,"updatedAt":3737,"url_path_id":3738,"contactPhoto":16,"socialLinks":3739,"url_path":3740},304,"Gouhei Tanaka","Nagoya Institute of Technology","2024-12-13T23:37:44.339Z","355",[],"-151",{"id":3742,"name":3743,"committee":16,"position":16,"affiliation":3744,"email":16,"biography":63,"createdAt":3745,"updatedAt":3745,"url_path_id":3746,"contactPhoto":16,"socialLinks":3747,"url_path":3748},452,"Ziqiang Li","International Research Center for Neurointelligence","2024-12-24T08:50:11.943Z","577",[],"-367",{"id":3750,"name":3751,"committee":16,"position":16,"affiliation":3752,"email":16,"biography":63,"createdAt":3753,"updatedAt":3753,"url_path_id":3754,"contactPhoto":16,"socialLinks":3755,"url_path":3756},453,"Xavier Hinaut","Inria","2024-12-24T08:50:26.194Z","578",[],"-372","-373",{"id":3759,"session":3760},74,{"id":283,"title":3761,"teaser":3762,"body":3763,"createdAt":3764,"updatedAt":3765,"publishedAt":3766,"url_path_id":3767,"contacts":3768,"url_path":3826},"Responsible Foundation Models in the Wild","\u003Cp style=\"text-align:justify;\">With the fast development of machine learning algorithms, foundation models (FMs) have been proposed to address multiple tasks at the same time. A well-known example is ChatGPT which has significantly impacted various aspects of our daily lives. \u003C/p>","\u003Cp style=\"text-align:justify;\">Recent achievements of FMs have positioned neural network architectures as both a powerful solution and one of the most promising methodologies for advancing toward artificial general intelligence (AGI). Although FMs have shown great abilities in solving many problems, they still face significant challenges concerning reliability when deploying them in real-world environments. For instance, FMs are known to hallucinate something or generate misleading or unethical outputs that conflict with human values, putting critical decisions at risk. Meanwhile, the training source of FMs might not be reliable either. In the current era, there are ever-growing, diverse, and unpredictable information sources, posing a huge challenge in training reliable FMs. Thus, as the potential applications of FMs continue to expand, it is urgent to push studies regarding trusted and responsible FMs. The powerful capabilities and broad applicability of FMs highlight the need for responsible design and usage, emphasizing the importance of enhanced interpretability, trustworthiness, and new learning paradigms to meet these evolving requirements. Addressing these challenges requires a deeper understanding of both the theoretical foundations and the evolving methodologies or applications of FMs. This special session aims to provide a forum for researchers to share the latest advantages in theories, algorithms, models and applications of FMs.\u003C/p>","2024-12-24T08:47:27.803Z","2024-12-24T08:47:30.888Z","2024-12-24T08:47:30.884Z","576",[3769,3777,3785,3793,3795,3803,3811,3819],{"id":3770,"name":3771,"committee":16,"position":16,"affiliation":3772,"email":16,"biography":63,"createdAt":3773,"updatedAt":3773,"url_path_id":3774,"contactPhoto":16,"socialLinks":3775,"url_path":3776},451,"Yiliao Song","The University of Adelaide","2024-12-24T08:46:33.287Z","575",[],"-370",{"id":3778,"name":3779,"committee":16,"position":16,"affiliation":3780,"email":16,"biography":63,"createdAt":3781,"updatedAt":3781,"url_path_id":3782,"contactPhoto":16,"socialLinks":3783,"url_path":3784},450,"Xuefeng Du","University of Wisconsin-Madison","2024-12-24T08:46:17.411Z","574",[],"-369",{"id":3786,"name":3787,"committee":16,"position":16,"affiliation":3788,"email":16,"biography":63,"createdAt":3789,"updatedAt":3789,"url_path_id":3790,"contactPhoto":16,"socialLinks":3791,"url_path":3792},449,"Zijian Wang","University of Queensland","2024-12-24T08:46:03.621Z","573",[],"-368",{"id":2525,"name":2526,"committee":16,"position":16,"affiliation":1349,"email":16,"biography":63,"createdAt":2527,"updatedAt":2528,"url_path_id":2529,"contactPhoto":16,"socialLinks":3794,"url_path":2531},[],{"id":3796,"name":3797,"committee":16,"position":16,"affiliation":3798,"email":16,"biography":63,"createdAt":3799,"updatedAt":3799,"url_path_id":3800,"contactPhoto":16,"socialLinks":3801,"url_path":3802},447,"Yadan Luo","The University of Queensland","2024-12-24T08:45:25.454Z","571",[],"-366",{"id":3804,"name":3805,"committee":16,"position":16,"affiliation":3806,"email":16,"biography":16,"createdAt":3807,"updatedAt":3807,"url_path_id":3808,"contactPhoto":16,"socialLinks":3809,"url_path":3810},286,"Feng Liu","UTS/RIKEN","2024-12-13T23:37:37.989Z","337",[],"-133",{"id":3812,"name":3813,"committee":16,"position":16,"affiliation":3814,"email":16,"biography":16,"createdAt":3815,"updatedAt":3815,"url_path_id":3816,"contactPhoto":16,"socialLinks":3817,"url_path":3818},271,"Dong Gong","The University of New South Wales","2024-12-13T23:37:33.081Z","322",[],"-118",{"id":3820,"name":3821,"committee":16,"position":16,"affiliation":3780,"email":16,"biography":63,"createdAt":3822,"updatedAt":3822,"url_path_id":3823,"contactPhoto":16,"socialLinks":3824,"url_path":3825},446,"Yixuan Li","2024-12-24T08:45:07.326Z","570",[],"-365","-371",{"id":283,"session":3828},{"id":3682,"title":3829,"teaser":3830,"body":3831,"createdAt":3832,"updatedAt":3833,"publishedAt":3834,"url_path_id":3835,"contacts":3836,"url_path":3844},"SAFE machine learning","\u003Cp style=\"text-align:justify;\">The growth of neural network applications requires to develop risk management models that can balance opportunities with risks. In the session, we contribute to the development of neural network risk models presenting a set of integrated statistical metrics that can measure the ``Sustainability'', ``Accuracy'', ``Fairness'' and ``Explainability'' of any Artificial Intelligence application, in line with  the requests of the European Artificial intelligence act. \u003C/p>","\u003Cp style=\"text-align:justify;\">The proposed metrics are consistent with each other, as they are all derived from a common underlying statistical methodology.  They are very general and can be applied to any machine learning method, regardless of the underlying data and model. Their empirical validity will be assessed by means of their practical application to a set of use cases. The application reveals that the proposed metrics are more interpretable and more consistent with the expectations, with respect to the currently used assessment metrics such as Mean Squared Error, Area Under the Curve, Shapley values and Fairness parity.\u003C/p>","2024-12-24T08:36:55.758Z","2024-12-24T08:36:59.487Z","2024-12-24T08:36:59.483Z","565",[3837],{"id":1462,"name":3838,"committee":16,"position":16,"affiliation":3839,"email":16,"biography":63,"createdAt":3840,"updatedAt":3840,"url_path_id":3841,"contactPhoto":16,"socialLinks":3842,"url_path":3843},"Paolo Giudici","University of Pavia","2024-12-24T08:36:45.067Z","564",[],"-359","-360",{"id":780,"session":3846},{"id":265,"title":3847,"teaser":3848,"body":3849,"createdAt":3850,"updatedAt":3851,"publishedAt":3852,"url_path_id":3853,"contacts":3854,"url_path":3894},"Self-organizing Clustering for Continual Learning and its Applications","\u003Cp style=\"text-align:justify;\">The motivation for this special session stems from the need to explore and advance the field of continual learning, a critical area in artificial intelligence that seeks to emulate the human ability to learn from experiences in an ongoing manner. The continual structuration of information and knowledge is essential for the development of intelligent systems capable of adapting to new environments, learning from their own experiences, and acquiring more complex knowledge over time. \u003C/p>","\u003Cp style=\"text-align:justify;\">Our aim is to foster a deeper understanding of how continual learning can be achieved through self-organizing clustering, adaptation, and cognitive development in dynamic environments. The objectives of this special session are to bring together researchers and practitioners to discuss novel approaches, methodologies, and applications in the field of continual learning, focusing particularly on self-organizing clustering algorithms. These algorithms have the potential to revolutionize the way intelligent systems are designed by allowing for more autonomous and adaptive learning processes. We aim to bridge theoretical foundations with real-world applications, thereby fostering interdisciplinary discussions and innovation.\u003C/p>","2024-12-24T08:53:54.614Z","2024-12-24T08:53:56.871Z","2024-12-24T08:53:56.866Z","584",[3855,3863,3871,3879,3887],{"id":3856,"name":3857,"committee":16,"position":16,"affiliation":3858,"email":16,"biography":63,"createdAt":3859,"updatedAt":3859,"url_path_id":3860,"contactPhoto":16,"socialLinks":3861,"url_path":3862},454,"Yuichiro Toda","Okayama University","2024-12-24T08:52:32.742Z","580",[],"-374",{"id":3864,"name":3865,"committee":16,"position":16,"affiliation":3866,"email":16,"biography":63,"createdAt":3867,"updatedAt":3867,"url_path_id":3868,"contactPhoto":16,"socialLinks":3869,"url_path":3870},455,"Naoki Masuyama","Osaka Metropolitan University","2024-12-24T08:52:46.668Z","581",[],"-375",{"id":3872,"name":3873,"committee":16,"position":16,"affiliation":3874,"email":16,"biography":16,"createdAt":3875,"updatedAt":3875,"url_path_id":3876,"contactPhoto":16,"socialLinks":3877,"url_path":3878},258,"Chu Kiong Loo","University of Malaya","2024-12-13T23:37:29.059Z","309",[],"-105",{"id":3880,"name":3881,"committee":16,"position":16,"affiliation":3882,"email":16,"biography":63,"createdAt":3883,"updatedAt":3883,"url_path_id":3884,"contactPhoto":16,"socialLinks":3885,"url_path":3886},456,"Stefan Wermter","University of Hamburg","2024-12-24T08:53:01.525Z","582",[],"-376",{"id":3888,"name":3889,"committee":16,"position":16,"affiliation":3874,"email":16,"biography":63,"createdAt":3890,"updatedAt":3890,"url_path_id":3891,"contactPhoto":16,"socialLinks":3892,"url_path":3893},457,"Wei Shuing Liew","2024-12-24T08:53:15.916Z","583",[],"-377","-378",{"id":265,"session":3896},{"id":3897,"title":3898,"teaser":3899,"body":3900,"createdAt":3901,"updatedAt":3902,"publishedAt":3903,"url_path_id":3904,"contacts":3905,"url_path":3937},79,"Sustainable AI for Internet-of-Things (IoT) networks","\u003Cp style=\"text-align:justify;\">Artificial Intelligence (AI), specifically Neural Networks (NNs), is transforming the landscape of pervasive computing, connectivity, and intelligence across various applications. Integrating AI into Internet-of-Things (IoT) and communication networks is essential for the future of sectors such as intelligent transportation systems, robotics, and telemedicine. \u003C/p>","\u003Cp style=\"text-align:justify;\">These applications often leverage complex NNs, which demand significant processing power and storage, potentially leading to increased carbon footprints. The rising energy demands of AI systems highlight the need for distributed and energy-efficient solutions that promote sustainability. Emerging paradigms in computing are increasingly prioritizing environmentally friendly methods, such as low-bit quantization of NNs and Tiny ML, that reduce storage requirements and minimize power consumption. This special session invites contributions from both industry and academia to explore these innovative solutions and their implications for the future of AI-driven technologies. The special session aims to address sustainability related issues of AI and NNs and absolutely lies within the scope of IJCNN 2025. Given that the regular ‘Call for Papers’ of IJCNN 2025 does not yet cover topics related to energy and sustainability, and therefore, a special session would also be useful to address global environmental challenges. The session’s objectives also support the United Nations Sustainable Development Goals, specifically those related to industry, innovation and infrastructure, and sustainable cities and communities. The special issue will be promoted and sponsored by IEEE Young Professionals Climate and Sustainability Task Force.\u003C/p>","2024-12-24T08:56:16.768Z","2024-12-24T08:56:19.428Z","2024-12-24T08:56:19.423Z","587",[3906,3913,3921,3929],{"id":844,"name":3907,"committee":16,"position":16,"affiliation":3908,"email":16,"biography":16,"createdAt":3909,"updatedAt":3909,"url_path_id":3910,"contactPhoto":16,"socialLinks":3911,"url_path":3912},"Ferheen Ayaz","City St. George's, University of London","2024-12-13T23:37:38.324Z","338",[],"-134",{"id":3914,"name":3915,"committee":16,"position":16,"affiliation":3916,"email":16,"biography":63,"createdAt":3917,"updatedAt":3917,"url_path_id":3918,"contactPhoto":16,"socialLinks":3919,"url_path":3920},459,"Polat Goktas","University College Dublin","2024-12-24T08:55:54.153Z","586",[],"-380",{"id":3922,"name":3923,"committee":16,"position":16,"affiliation":3924,"email":16,"biography":16,"createdAt":3925,"updatedAt":3925,"url_path_id":3926,"contactPhoto":16,"socialLinks":3927,"url_path":3928},234,"Amani Ibraheem","KKU","2024-12-13T23:37:22.020Z","285",[],"-81",{"id":3930,"name":3931,"committee":16,"position":16,"affiliation":3932,"email":16,"biography":63,"createdAt":3933,"updatedAt":3933,"url_path_id":3934,"contactPhoto":16,"socialLinks":3935,"url_path":3936},458,"Zhengguo Sheng","University of Sussex","2024-12-24T08:55:36.503Z","585",[],"-379","-381",{"id":3897,"session":3939},{"id":3940,"title":3941,"teaser":3942,"body":3943,"createdAt":3944,"updatedAt":3945,"publishedAt":3946,"url_path_id":3947,"contacts":3948,"url_path":3963},80,"Synergies between Quantum Computing and Machine Learning","\u003Cp style=\"text-align:justify;\">Quantum Machine Learning (QML) is an emerging interdisciplinary field at the intersection of quantum computing and machine learning. This is an area of growing interest because QML exploits the computational advantages of quantum mechanics to potentially develop more efficient algorithms capable of solving problems that are infeasible for classical methods. \u003C/p>","\u003Cp style=\"text-align:justify;\">In detail, traditional machine learning methods have shown remarkable success in numerous domains, but they are reaching computational limits as the size and complexity of data. Quantum computing, leveraging principles such as superposition, entanglement, and quantum interference, offers a fundamentally new approach to processing information, with the potential to address these limitations and enhance machine learning capabilities. The special session on QML aims to: i)Discuss the latest developments in quantum algorithms for supervised, unsupervised, and reinforcement learning tasks. ii) Explore hybrid quantum-classical models, which combine the strengths of quantum computing with classical machine learning methods. iii) Discuss practical applications and real-world use cases demonstrating the potential advantages of QML.\u003C/p>","2024-12-24T08:57:28.018Z","2024-12-24T08:57:30.685Z","2024-12-24T08:57:30.679Z","588",[3949,3957],{"id":3950,"name":3951,"committee":16,"position":16,"affiliation":3952,"email":16,"biography":16,"createdAt":3953,"updatedAt":3953,"url_path_id":3954,"contactPhoto":16,"socialLinks":3955,"url_path":3956},301,"Giovanni Acampora","University of Naples Federico II","2024-12-13T23:37:43.215Z","352",[],"-148",{"id":1107,"name":3958,"committee":16,"position":16,"affiliation":3952,"email":16,"biography":16,"createdAt":3959,"updatedAt":3959,"url_path_id":3960,"contactPhoto":16,"socialLinks":3961,"url_path":3962},"Autilia Vitiello","2024-12-13T23:37:26.106Z","299",[],"-95","-382",{"id":3940,"session":3965},{"id":3966,"title":3967,"teaser":3968,"body":3969,"createdAt":3970,"updatedAt":3971,"publishedAt":3972,"url_path_id":3973,"contacts":3974,"url_path":4007},81,"Systems-Theoretic Approaches to Learning II: Applications to System Identification, State Estimation and Control","\u003Cp style=\"text-align:justify;\">The application of dynamical systems theory to enhance learning efficiency has gained traction due to its ability to improve explainability, interpretability, and provide provable guarantees. By offering a structured framework to analyze information flow, stability, and convergence, dynamical systems theory strengthens deep learning models, enabling better performance and robustness. This perspective transforms optimization into a control problem, streamlining processes such as hyperparameter tuning and convergence analysis. \u003C/p>","\u003Cp style=\"text-align:justify;\">Recent advancements include innovative approaches like Neural ODEs, which enhance memory efficiency and adaptability; Physics-Informed Neural Networks (PINNs) that incorporate physical laws for improved generalization with limited data; and data-driven techniques such as Sparse Identification of Nonlinear Dynamics (SINDy), Pseudo Spectral Methods (PSM) and Koopman Operator Theory (KOT) for uncovering governing equations. The special session will focus on system theory's role in advancing learning algorithms, particularly in dynamic environments. It will feature cutting-edge developments at the intersection of systems-theoretic principles and learning methodologies, emphasizing both foundational frameworks and practical applications. \u003C/p>\u003Cp style=\"text-align:justify;\">Key topics include real-time and lifelong learning, adaptive control in deep neural networks, reinforcement learning in single and multi-agent systems, adaptive dynamic programming for optimal control in evolving systems, physics-informed neural networks, neural ordinary differential equations (ODEs), system identification using SINDy, KOT, adn PSM. Expert researchers in these areas will present their research findings demonstrating how integrating systems theory enhances performance, robustness, and interpretability in traditional learning-based approaches. Attendees will delve into the synergy between dynamic systems theory and machine learning, uncovering insights into how these domains complement and strengthen one another. This special session promises a comprehensive exploration of innovative approaches and their transformative potential for modern learning paradigms.\u003C/p>","2024-12-24T08:59:30.149Z","2024-12-24T08:59:32.789Z","2024-12-24T08:59:32.784Z","590",[3975,3983,3991,3999],{"id":3976,"name":3977,"committee":16,"position":16,"affiliation":3978,"email":16,"biography":16,"createdAt":3979,"updatedAt":3979,"url_path_id":3980,"contactPhoto":16,"socialLinks":3981,"url_path":3982},249,"Avimanyu Sahoo","The University of Alabama in Huntsville","2024-12-13T23:37:26.416Z","300",[],"-96",{"id":3984,"name":3985,"committee":16,"position":16,"affiliation":3986,"email":16,"biography":63,"createdAt":3987,"updatedAt":3987,"url_path_id":3988,"contactPhoto":16,"socialLinks":3989,"url_path":3990},460,"Vignesh Narayanan","University of South Carolina","2024-12-24T08:59:01.893Z","589",[],"-383",{"id":3992,"name":3993,"committee":16,"position":16,"affiliation":3994,"email":16,"biography":16,"createdAt":3995,"updatedAt":3995,"url_path_id":3996,"contactPhoto":16,"socialLinks":3997,"url_path":3998},311,"Hao Xu","University of Nevada Reno","2024-12-13T23:37:47.309Z","362",[],"-158",{"id":4000,"name":4001,"committee":16,"position":16,"affiliation":4002,"email":16,"biography":16,"createdAt":4003,"updatedAt":4003,"url_path_id":4004,"contactPhoto":16,"socialLinks":4005,"url_path":4006},338,"Krishnan Raghavan","Argonne National Laboratory","2024-12-13T23:37:59.526Z","389",[],"-185","-384",{"id":654,"session":4009},{"id":3759,"title":4010,"teaser":4011,"body":4012,"createdAt":4013,"updatedAt":4014,"publishedAt":4015,"url_path_id":4016,"contacts":4017,"url_path":4020},"Tiny Machine Learning","\u003Cp style=\"text-align:justify;\">The computing everywhere paradigm is paving the way for the pervasive diffusion of tiny devices endowed with intelligent abilities (such as Internet-of-things and edge computing devices). \u003C/p>","\u003Cp style=\"text-align:justify;\">Achieving this goal requires machine and deep learning solutions to be completely redesigned to fit the stringent technological constraints on computation, memory, and power consumption that typically characterize these tiny devices. This is exactly where Tiny Machine Learning (TinyML) comes into play. TinyML is a new and promising area of Machine Learning aimed at designing and developing Machine and Deep Learning solutions that can be executed on tiny devices. This special session aims at exploring the latest advancements, models, algorithms, methodologies, and applications in TinyML.\u003C/p>","2024-12-24T08:38:39.367Z","2024-12-24T08:38:42.582Z","2024-12-24T08:38:42.577Z","566",[4018],{"id":3620,"name":3621,"committee":16,"position":16,"affiliation":3375,"email":16,"biography":16,"createdAt":3622,"updatedAt":3622,"url_path_id":3623,"contactPhoto":16,"socialLinks":4019,"url_path":3625},[],"-361",{"id":3966,"session":4022},{"id":4023,"title":4024,"teaser":4025,"body":4026,"createdAt":4027,"updatedAt":4028,"publishedAt":4029,"url_path_id":4030,"contacts":4031,"url_path":4067},82,"Trustworthy and Explainable Federated Learning: Towards Security and Privacy Future","\u003Cp style=\"text-align:justify;\">The motivation for this special session on Federated Learning (FL) at IJCNN 2025 stems from FL's transformative role in enabling collaborative machine learning across industries while safeguarding user privacy and data security. FL's applications in healthcare, finance, telecommunications, smart cities, retail, automotive, and education demonstrate its versatility and value in leveraging decentralized data to achieve personalized services, fraud detection, network optimization, autonomous driving, adaptive learning, and more. By reducing data transfer, democratizing AI, ensuring regulatory compliance, and minimizing bias, FL has positioned itself as a crucial tool in today's data-driven world. \u003C/p>","\u003Cp style=\"text-align:justify;\">The specific FL applications for example, in healthcare, it facilitates personalized medicine and disease research without sharing sensitive patient data. The finance sector employs FL for fraud detection and credit scoring, leveraging decentralized data while ensuring privacy. Telecommunications and smart cities benefit from network optimization and urban planning, respectively, without centralizing user data. In retail, FL aids in personalized shopping experiences and supply chain management. The automotive industry uses it to improve autonomous vehicle algorithms, and educational institutions apply it to create adaptive learning systems. The significance of FL lies in its capacity to preserve privacy, enhance security, ensure regulatory compliance, reduce data transfer costs, facilitate real-time learning, democratize AI, and mitigate biases, making it an invaluable tool in the era of data-driven decision-making. \u003C/p>\u003Cp style=\"text-align:justify;\">However, FL faces notable security and privacy challenges despite its advantages in decentralized learning. These include data and model poisoning attacks where malicious actors manipulate data or model updates, inference attacks that can deduce sensitive information from model updates, and privacy leakage during aggregation. Sybil attacks, where an adversary creates multiple fake identities, also pose a threat to the integrity of FL systems. Additionally, the non-IID nature of real-world data, communication overhead, and the need for secure transmission of model updates are significant concerns. The variability in client participation and the challenge of balancing model accuracy with privacy, especially under regulatory and compliance constraints, further complicate the effective implementation of FL. \u003C/p>\u003Cp style=\"text-align:justify;\">Addressing these issues is vital for the practical and secure application of FL in various domains. The special session aims to bring together researchers, practitioners, and industry experts to discuss and advance the frontiers of FL in the context of trustworthiness and explainability. The focus will be on addressing the emerging challenges related to security, privacy, and transparency in FL systems. The session will explore innovative methods and strategies to ensure that federated learning models are not only effective and efficient but also secure, privacypreserving, and comprehensible to users and stakeholders. The ultimate goal is to foster the development of FL solutions that are robust against adversarial attacks, respectful of user privacy, and transparent in their decision-making processes.\u003C/p>","2024-12-24T09:01:49.540Z","2024-12-24T09:02:03.927Z","2024-12-24T09:02:03.916Z","592",[4032,4034,4041,4043,4051,4059],{"id":2201,"name":2202,"committee":16,"position":16,"affiliation":2203,"email":16,"biography":16,"createdAt":2204,"updatedAt":2204,"url_path_id":2205,"contactPhoto":16,"socialLinks":4033,"url_path":2207},[],{"id":4035,"name":4036,"committee":16,"position":16,"affiliation":2203,"email":16,"biography":16,"createdAt":4037,"updatedAt":4037,"url_path_id":4038,"contactPhoto":16,"socialLinks":4039,"url_path":4040},331,"Jun Bai","2024-12-13T23:37:56.288Z","382",[],"-178",{"id":3770,"name":3771,"committee":16,"position":16,"affiliation":3772,"email":16,"biography":63,"createdAt":3773,"updatedAt":3773,"url_path_id":3774,"contactPhoto":16,"socialLinks":4042,"url_path":3776},[],{"id":4044,"name":4045,"committee":16,"position":16,"affiliation":4046,"email":16,"biography":16,"createdAt":4047,"updatedAt":4047,"url_path_id":4048,"contactPhoto":16,"socialLinks":4049,"url_path":4050},324,"Jing Xu","CISPA","2024-12-13T23:37:52.998Z","375",[],"-171",{"id":4052,"name":4053,"committee":16,"position":16,"affiliation":4054,"email":16,"biography":16,"createdAt":4055,"updatedAt":4055,"url_path_id":4056,"contactPhoto":16,"socialLinks":4057,"url_path":4058},321,"Jiale Zhang","Yangzhou University","2024-12-13T23:37:51.709Z","372",[],"-168",{"id":4060,"name":4061,"committee":16,"position":16,"affiliation":4062,"email":16,"biography":63,"createdAt":4063,"updatedAt":4063,"url_path_id":4064,"contactPhoto":16,"socialLinks":4065,"url_path":4066},461,"Youyang Qu","Shandong Computer Senter","2024-12-24T09:01:36.116Z","591",[],"-385","-386",{"id":4023,"session":4069},{"id":654,"title":4070,"teaser":4071,"body":4072,"createdAt":4073,"updatedAt":4074,"publishedAt":4075,"url_path_id":4076,"contacts":4077,"url_path":4107},"Trustworthy and Reliable Artificial Intelligence Applications in Healthcare Decision-Making","\u003Cp style=\"text-align:justify;\">The emergence of the big data era in healthcare has led to the widespread collection of health information in various forms, including electronic patient records, administrative claims data, biometric data, sensor data, and medical images. \u003C/p>","\u003Cp style=\"text-align:justify;\">Artificial Intelligence (AI) and machine learning techniques are increasingly being employed to extract valuable insights from this complex data, transforming it into actionable knowledge that supports improved healthcare decision-making and outcomes. However, significant challenges remain in the application of AI within healthcare. Practical issues like low-quality training data, the opacity of AI models (black box problems), algorithmic bias and fairness concerns, and data privacy risks pose barriers to the effective integration of AI into existing healthcare systems. Addressing these challenges is crucial for AI to achieve broader adoption and meaningful impact in transforming healthcare. This special session aims to present recent advancements in applied AI, focusing on solutions to emerging challenges and the development of reliable, trustworthy intelligent systems in healthcare and medicine. It will also serve as a global platform to share and discuss the latest research aimed at delivering patient-centered, outcome-driven, and effective healthcare through the use of AI.\u003C/p>","2024-12-24T09:03:43.315Z","2024-12-24T09:03:46.423Z","2024-12-24T09:03:46.418Z","594",[4078,4086,4093,4095,4097,4105],{"id":4079,"name":4080,"committee":16,"position":16,"affiliation":4081,"email":16,"biography":16,"createdAt":4082,"updatedAt":4082,"url_path_id":4083,"contactPhoto":16,"socialLinks":4084,"url_path":4085},345,"Lourdes Martinez-Villaseñor","Universidad Panamericana","2024-12-13T23:38:03.758Z","396",[],"-192",{"id":4087,"name":4088,"committee":16,"position":16,"affiliation":4081,"email":16,"biography":16,"createdAt":4089,"updatedAt":4089,"url_path_id":4090,"contactPhoto":16,"socialLinks":4091,"url_path":4092},313,"Hiram Ponce","2024-12-13T23:37:48.196Z","364",[],"-160",{"id":1743,"name":1744,"committee":16,"position":16,"affiliation":1745,"email":16,"biography":16,"createdAt":1746,"updatedAt":1746,"url_path_id":1747,"contactPhoto":16,"socialLinks":4094,"url_path":1749},[],{"id":1998,"name":1999,"committee":16,"position":16,"affiliation":1761,"email":16,"biography":63,"createdAt":2000,"updatedAt":2000,"url_path_id":2001,"contactPhoto":16,"socialLinks":4096,"url_path":2003},[],{"id":4098,"name":4099,"committee":16,"position":16,"affiliation":4100,"email":16,"biography":63,"createdAt":4101,"updatedAt":4101,"url_path_id":4102,"contactPhoto":16,"socialLinks":4103,"url_path":4104},462,"Rui Chen","Samsung Research America","2024-12-24T09:03:33.408Z","593",[],"-387",{"id":2341,"name":2342,"committee":16,"position":16,"affiliation":2316,"email":16,"biography":16,"createdAt":2343,"updatedAt":2343,"url_path_id":2344,"contactPhoto":16,"socialLinks":4106,"url_path":2346},[],"-388",{"id":673,"session":4109},{"id":673,"title":4110,"teaser":4111,"body":4112,"createdAt":4113,"updatedAt":4114,"publishedAt":4115,"url_path_id":4116,"contacts":4117,"url_path":4140},"Towards Robust Federated Learning: Addressing Data and Device Heterogeneity","\u003Cp style=\"text-align:justify;\">Federated Learning (FL) has emerged as a groundbreaking approach to enabling AI across decentralized and sensitive data sources without requiring data centralization, addressing privacy concerns that align with regulations like GDPR. For a leading conference like IJCNN, which emphasizes advancements in neural networks and transformative AI, FL offers a rich avenue for exploration. \u003C/p>","\u003Cp style=\"text-align:justify;\">While past sessions at IJCNN (see IJCNN 2024) have largely focused on privacy and trustworthiness, the next critical frontier is addressing the inherent challenges of non-iid data distributions and device heterogeneity—barriers that must be overcome for FL to scale and perform effectively in real-world settings. In practical FL deployments, data generated across decentralized sources is not only non-iid but is also produced by diverse devices with varying computational power, network stability, and memory capacity. \u003C/p>\u003Cp style=\"text-align:justify;\">This device heterogeneity complicates learning, as not all devices can contribute equally or reliably. Such variability can degrade model performance, create biases, and complicate both convergence and fairness. For example, FL applications in healthcare and IoT span a range of devices, from powerful servers to lightweight edge devices, each with unique data characteristics and resource constraints. Addressing non-iid data and device heterogeneity is essential for FL to be scalable, fair, and ethically viable, especially in critical areas like medical diagnostics and financial forecasting. \u003C/p>\u003Cp style=\"text-align:justify;\">This session at IJCNN 2024 aims to gather the global FL research community to address the dual challenges of non-iid data and device heterogeneity. These issues present significant technical and theoretical hurdles that require novel solutions. We invite contributions that focus on handling the variability inherent in data and devices to make FL robust and practical for diverse applications.\u003C/p>","2024-12-24T09:05:46.776Z","2024-12-24T09:05:52.496Z","2024-12-24T09:05:52.492Z","595",[4118,4126,4133],{"id":4119,"name":4120,"committee":16,"position":16,"affiliation":3952,"email":16,"biography":63,"createdAt":4121,"updatedAt":4122,"url_path_id":4123,"contactPhoto":16,"socialLinks":4124,"url_path":4125},268,"Diletta Chiaro","2024-12-13T23:37:32.163Z","2025-03-17T13:15:03.690Z","319",[],"-115",{"id":4127,"name":4128,"committee":16,"position":16,"affiliation":3952,"email":16,"biography":16,"createdAt":4129,"updatedAt":4129,"url_path_id":4130,"contactPhoto":16,"socialLinks":4131,"url_path":4132},294,"Francesco Piccialli","2024-12-13T23:37:40.721Z","345",[],"-141",{"id":4134,"name":4135,"committee":16,"position":16,"affiliation":3952,"email":16,"biography":16,"createdAt":4136,"updatedAt":4136,"url_path_id":4137,"contactPhoto":16,"socialLinks":4138,"url_path":4139},280,"Fabio Giampaolo","2024-12-13T23:37:35.975Z","331",[],"-127","-389",{"data":4142,"meta":4143},{"id":317,"heading":311,"createdAt":318,"updatedAt":319,"publishedAt":320,"url_path_id":321,"url_path":313,"contentType":101},{},1778852697121]