Dynamic Deep Learning | Richard Sutton

ICARL Seminar Series - 2024 Winter

Dynamic Deep Learning
Seminar by Richard Sutton

——————————————————
Abstract:

Despite great successes, current deep learning methods cannot learn effectively during normal operation, which makes them ill-suited for reinforcement learning or, really, for any general intelligence. In particular, conventional artificial neural networks fail catastrophically in classic supervised learning testbeds, such as ImageNet, when those testbeds are extended to require ongoing learning. In this talk, I argue that this failure is not inherent in neural networks, but just of the algorithms currently used. For example, a simple modification of the standard backpropagation algorithm, known as continual backpropagation, greatly improves performance in continual learning settings. Such results suggest exploring network learning algorithms explicitly designed for continual and reversible change, such as Dynamic deep learning networks, which continually adapt at multiple levels including 1) their weights, 2) their step-size parameters, and 3) their interconnection structure.

——————————————————
About the Speaker:

Rich Sutton is research scientist at Keen Technologies, professor in the Department of Computing Science at the University of Alberta, chief scientific advisor of the Alberta Machine Intelligence Institute (Amii), and fellow of the Royal Society of London, the Royal Society of Canada, the Association for the Advancement of Artificial Intelligence, Amii, and CIFAR. He received a PhD in computer science from the University of Massachusetts in 1984 and a BA in psychology from Stanford University in 1978. Prior to joining the University of Alberta in 2003, he worked in industry at AT&T Labs and GTE Labs, and in academia at the University of Massachusetts. He helped found DeepMind Alberta in 2017 and worked there until its dissolution in 2023. At the University of Alberta, Sutton founded the Reinforcement Learning and Artificial Intelligence Lab, which now consists of ten principal investigators and about 100 people altogether. Sutton is co-author of the textbook Reinforcement Learning: An Introduction, and his scientific publications have been cited more than 140,000 times. He is also a libertarian, a chess player, and a cancer survivor.

——————————————————
Links
Richard Sutton
Site: incompleteideas.net
Twitter: x.com/RichardSSutton

ICARL
Site: icarl.doc.ic.ac.uk
Twitter: x.com/ic_arl
YouTube: @ICARLSeminars
——————————————————