Conference on Advances in Data Science: Talk Titles & Abstracts for Invited Speakers

Edison Thomaz, University of Texas at Austin

Talk Title: Continual Learning for Behavior Monitoring with Prototypical Networks

Abstract: Continual learning (CL), also known as lifelong learning, is an emerging research topic that has been attracting increasing interest in the field of machine learning. With human activity recognition (HAR) playing a key role in enabling numerous real-world applications, an essential step towards the long-term deployment of such systems is to extend the activity model to dynamically adapt to changes in people’s everyday behavior. In this talk, I will present a lifelong adaptive learning framework using Prototypical Networks, LAPNet- HAR, that processes sensor-based data streams in a task-free data-incremental fashion and mitigates catastrophic forgetting using experience replay and continual prototype adaptation. Our extensive empirical results demonstrate the effectiveness of LAPNet-HAR in task-free CL and uncover useful insights for future challenges.