Workshops

This special INNS-sponsored workshop aims to explore innovations and applications of deep Learning and bring together academic researchers and industry professionals. Authors will be invited to submit a paper in the second edition of the INNS workshop series in Procedia Computer Science (open access). 

Topics for the workshop include:

• Deep Learning Applications in the areas such as healthcare, finance, education, visual recognition, entertainment, personalisation, fraud detection, autonomous driving, bioinformatics and others
• Graph Neural Networks
• Reinforcement learning
• Generative Neural Networks
• Deep Neural Networks for computer vision
• Deep Neural Networks for natural language processing
• Deep leaning and ethics
• Explainability and emerging issues

The workshop participation will be online with links to the presentations and abstracts of the accepted papers.

Important Dates

Camera-ready upload:  15 June 2025
Workshop dates: 30 June - 5 July 2025 

Submission Guidelines

Authors must follow the submission guidelines found on the Elsevier website. Contributions should have 8 - 10 pages, references included.

Submission process will be via a dedicated link that will be confirmed by email to the corresponding authors of the accepted papers.

The SIREN workshop explores how Artificial Intelligence can tackle critical social challenges. By bridging advanced AI research with practical applications, the event encourages the development of impactful solutions that benefit society. 

The COP29 Declaration on Green Digital Action highlights the critical role of digital technologies in combating climate change. The workshop will focus on multiple applications of neural networks within environmental science and sustainable development. 

"We are pleased to announce a workshop dedicated to exploring the latest advancements in Artificial Intelligence (AI), with a particular emphasis on its applications in education. 

The AI Policy and Regulation workshop responds to the imminent global AI policy and regulatory changes that have profound implications for AI and Neural Networks research and industry deployment.

AIMB workshop addresses the transformative potential of artificial intelligence (AI) and neural networks (NNs) in healthcare and life sciences, focusing on the development of specialized techniques for complex biological data. 

On-device training using edge compu+ng allows intelligent devices to learn autonomously while improving latency and security. 

The AICI workshop will focus on recent applications of AI techniques in Critical Infrastructure research, education and innovation for development, operations, and management, specifically focused on: AI for modelling critical infrastructure systems, AI for control and operations, AI for critical infrastructure optimization.The panelist, mainly from industry, will present the ongoing activities in the AICI. 

The neural network and Bayesian machine learning communities have historically struggled to come together due to philosophical differences and different metrics of success. 

The "Computational Intelligence for Sustainable Energy Management in Microgrids and Renewable Energy Communities (CISEM 2025)" workshop addresses sustainable energy challenges by applying computational intelligence methods such as machine learning, evolutionary algorithms, and deep learning. 

Biometrics has become a burgeoning research area due to the industrial and government needs for recognition, security, and privacy concerns. 

Smart Grids are critical infrastructures to improve energy efficiency, and as they become increasingly complex, the need for advanced methods to monitor, analyze, and optimize them has never been more pressing. 

The rapid evolution of Smart Eyewear technology holds the potential to revolutionize daily life by seamlessly integrating artificial intelligence into wearable devices. 

As AI and ML technologies evolve, the environmental and energy costs associated with training large-scale models have become a growing concern. 

The "Forging Trust in Artificial Intelligence" workshop focuses on enhancing AI trustworthiness through transparency, fairness, and privacy.

The workshop delves into the convergence point between neural networks and the analysis of human behavior—focusing particularly on methodologies that shift from perceptual processes to predictive analytics. 

The workshop delves into advanced deep learning solutions for biomedical data analysis, promoting personalized medicine and digital prevention. 

The Workshop aims at providing concrete and original insights on quantum neural methods based on the current available technology in the Noisy Intermediate-Scale Quantum (NISQ) era, as quantum computing can potentially bring a disruptive innovation in the Computational Intelligence field, tackling problems from healthcare and bioinformatics to finance and cybersecurity, more in general for the modeling and control of real-world complex systems.

The "Robust AI in Healthcare" workshop explores strategies for developing safe, reliable, and efficient AI models for healthcare. It also helps to bridge the gap between AI research and practical deployment in healthcare. 

Saliency prediction, an important domain in machine learning and cognitive neuroscience, plays a crucial role in crafting intelligent systems that emulate human attention. 

Graph learning plays a pivotal role in modern AI, enabling the management of massive graphs, extracting insights from complex relationships, and enhancing model interpretability and fairness. 

SusAI workshop aims at gathering researchers to present new trends and highlight new ideas about sustainable AI. In particular, it will present approaches, both at the training and at the inference levels, for obtaining lighter models, requiring less energy for training and/or usable on edge devices. 
 

Neurosymbolic AI is a new growing trend that has been able to merge the recent advances in AI through deep learning with logic and rule-based methods. 

This workshop addresses the rising challenges of AI-generated content and deepfakes by exploring advancements in multimedia forensics, deepfake detection, adversarial machine learning, AI-generated media attribution, multimodal analysis.