Lecture Series in AI: Richard Zemel
Title: Integrating Past and Present in Continual Learning
Abstract: Continual learning aims to bridge the gap between typical human and machine-learning environments. The continual setting does not have separate training and testing phases, and instead models are evaluated online while learning novel concepts and tasks. The most capable current AI systems struggle to learn new knowledge sequentially without forgetting old ones. Challenging research questions include how to rapidly assess a learner system’s abilities and how to most efficiently train it to improve on a sequence of tasks. I will describe recent progress on these questions, across various research groups in ARNI, our NSF AI Institute for Artificial and Natural Intelligence. Finally we will consider open issues and challenges in continual learning.
Bio: Richard Zemel is the Trianthe Dakolias Professor of Engineering and Applied Science in the Computer Science Department at Columbia University.
He is the Director of the NSF AI Institute for Artificial and Natural Intelligence (ARNI), and was the co-founder and inaugural Research Director of the Vector Institute for Artificial Intelligence. His awards include an AI Lifetime Achievement Award (CAIA) and a Pioneer of AI Award (NVIDIA). His research contributions include foundational work on systems that learn useful representations of data with little or no supervision; graph-based machine learning; and algorithms for fair and robust machine learning.