PerconAI 2024: 3rd Workshop on Pervasive and Resource-Constrained Artificial Intelligence - Welcome and Committees

The PeRConAI workshop aims at promoting the circulation of new ideas and research directions on pervasive and resource-constrained artificial intelligence, serving as a forum for practitioners and researchers working on the intersection between pervasive computing and machine learning, including deep learning and artificial intelligence.The workshop welcomes theoretical and applied research sharing the common objective of investigating solutions advancing towards a truly pervasive and liquid AI.In the long term, we envision a future where every device at the edge of the Internet, regardless of its computing capabilities, will have an active role in the AI process by processing its data and collaborating with other devices to extract knowledge from them.The workshop international program committee refereed the submitted full papers by their quality and relevance to the theme.The final program includes eleven carefully selected papers out of seventeen submissions, including two papers redirected from the main conference.The workshop features a keynote speech and four technical sessions covering the different aspects of AI in pervasive computing.The first session regards human behaviors and activity recognition.The papers in the second session address problems related to augmented reality and edge computing.The third session mainly focuses on advanced neural networks and machine learning techniques,.while the fourth session entails federated learning and multi-device learning environments.A keynote speech will take place after the opening remarks, and it will be performed by Prof. Paul Lukowicz.We want to thank the program committee members for providing detailed and thoughtful reviews, thus making it possible to assemble an exciting program of high-quality papers.We would also like to thank the PerCom organizers, the PerCom workshop co-chairs, for supporting the workshop and assisting with its organization.Finally, we thank all authors and workshop attendees for their contributions and participation.