Bridging the gap between brains, cognition and deep learning

Yoshua Bengio, University of Montréal, introducing ideas from three decades ago which have fuelled a revolution in artificial intelligence with the rise of deep learning methods. Followed by a discussion of the new ideas from deep learning, including newly acquired theoretical understanding of the advantages brought by jointly optimizing a deep architecture. Finally, a summary of some of the recent work aimed at bridging the remaining gap between deep learning and neuroscience.

By INCF
Published Oct, 2018

Description

The talk starts by reviewing connectionist ideas from three decades ago which have fuelled a revolution in artificial intelligence with the rise of deep learning methods. Followed by a discussion of new ideas from deep learning, including a discussion of the newly acquired theoretical understanding of the advantages brought by jointly optimizing a deep architecture. Finally, Bengio summarize some of the recent work aimed at bridging the remaining gap between deep learning and neuroscience, including approaches to implement functional equivalents to backpropagation in a more biologically plausible way, as well as ongoing work connecting language, cognition, reinforcement learning and the learning of abstract representations.