Yoshua Bengio: The Past, Present, and Future of Deep Learning

Happy episode 50! This week’s episode is being released on Monday to avoid Thanksgiving.
Have suggestions for future podcast guests (or other feedback)? Let us know here (forms.gle/YNKGko9LCGNp1rhU7)!
In episode 50 of The Gradient Podcast, Daniel Bashir (twitter.com/spaniel_bashir) speaks to Professor Yoshua Bengio.
Professor Bengio is a Full Professor at the Université de Montréal (umontreal.ca) as well as Founder and Scientific Director of the MILA-Quebec AI Institute (mila.quebec/en) and the IVADO institute (ivado.ca/en). Best known for his work in pioneering deep learning, Bengio was one of three awardees (awards.acm.org/about/2018-turing) of the 2018 A.M. Turing Award along with Geoffrey Hinton (cs.toronto.edu/~hinton) and Yann LeCun (yann.lecun.com). He is also the awardee of the prestigious Killam prize (canadacouncil.ca/funding/prizes/killam-prizes) and, as of this year, the computer scientist with the highest h-index in the world (scholar.google.com/citations?user=kukA0LcAAAAJ…).
Subscribe to The Gradient Podcast: Apple Podcasts (podcasts.apple.com/us/podcast/the-gradient-pod…) | Spotify (open.spotify.com/show/6onNcSqsP6hEEqmZ6TU2g8) | Pocket Casts (pca.st/itunes/1569777340) | RSS (api.substack.com/feed/podcast/265424/s/1354/pr…)Follow The Gradient on Twitter (twitter.com/gradientpub)
Outline:
* (00:00) Intro
* (02:20) Journey into Deep Learning, PDP and Hinton
* (06:45) “Inspired by biology”
* (08:30) “Gradient Based Learning Applied to Document Recognition” and working with Yann LeCun
* (10:00) What Bengio learned from LeCun (and Larry Jackel) about being a research advisor
* (13:00) “Learning Long-Term Dependencies with Gradient Descent is Difficult,” why people don’t understand this paper well enough
* (18:15) Bengio’s work on word embeddings and the curse of dimensionality, “A Neural Probabilistic Language Model”
* (23:00) Adding more structure / inductive biases to LMs
* (24:00) The rise of deep learning and Bengio’s experience, “you have to be careful with inductive biases”
* (31:30) Bengio’s “Bayesian posture” in response to recent developments
* (40:00) Higher level cognition, Global Workspace Theory
* (45:00) Causality, actions as mediating distribution change
* (49:30) GFlowNets and RL
* (53:30) GFlowNets and actions that are not well-defined, combining with System II and modular, abstract ideas
* (56:50) GFlowNets and evolutionary methods
* (1:00:45) Bengio on Cartesian dualism
* (1:09:30) “When you are famous, it is hard to work on hard problems” (Richard Hamming) and Bengio’s response
* (1:11:10) Family background, art and its role in Bengio’s life
* (1:14:20) Outro
Links:
* Professor Bengio’s Homepage (yoshuabengio.org)
* Papers
* Gradient-based learning applied to document recognition (ieeexplore.ieee.org/document/726791)
* Learning Long-Term Dependencies with Gradient Descent is Difficult (comp.hkbu.edu.hk/~markus/teaching/comp7650/tnn…)
* The Consciousness Prior (arxiv.org/abs/1709.08568)
* Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation (arxiv.org/abs/2106.04399)

Get full access to The Gradient at thegradientpub.substack.com/subscribe?utm_medi…