The Importance of Sparse Coding in Neural Networks

A lot of the motivation was from neuroscience and also at the time you know if you look back at the um greedy layer eyes pre-training paper and a lot of paper in that area no one was using relu's rectified linear units. It was all tanh or maybe sigmoids, I remember when we the idea relu's came up in jeff's lab and also in yashua's lab a bit after or about the same time. So yeah so that particular paper of mine on interdependent neurons like that was very much very much uh a lot of the inspiration for this work is still there.

Transcript

chevron_right

Play full episode

chevron_right

Transcript

Episode notes

In episode 80 of The Gradient Podcast, Daniel Bashir speaks to Professor Hugo Larochelle.

Professor Larochelle leads the Montreal Google DeepMind team and is adjunct professor at Université de Montréal and a Canada CIFAR Chair. His research focuses on the study and development of deep learning algorithms.

Have suggestions for future podcast guests (or other feedback)? Let us know here or reach us at editor@thegradient.pub

Subscribe to The Gradient Podcast: Apple Podcasts | Spotify | Pocket Casts | RSSFollow The Gradient on Twitter

Outline:

* (00:00) Intro

* (01:38) Prof. Larochelle’s background, working in Bengio’s lab

* (04:53) Prof. Larochelle’s work and connectionism

* (08:20) 2004-2009, work with Bengio

* (08:40) Nonlocal Estimation of Manifold Structure, manifolds and deep learning

* (13:58) Manifold learning in vision and language

* (16:00) Relationship to Denoising Autoencoders and greedy layer-wise pretraining

* (21:00) From input copying to learning about local distribution structure

* (22:30) Zero-Data Learning of New Tasks

* (22:45) The phrase “extend machine learning towards AI” and terminology

* (26:55) Prescient hints of prompt engineering

* (29:10) Daniel goes on totally unnecessary tangent

* (30:00) Methods for training deep networks (strategies and robust interdependent codes)

* (33:45) Motivations for layer-wise pretraining

* (35:15) Robust Interdependent Codes and interactions between neurons in a single network layer

* (39:00) 2009-2011, postdoc in Geoff Hinton’s lab

* (40:00) Reflections on the AlexNet moment

* (41:45) Frustration with methods for evaluating unsupervised methods, NADE

* (44:45) How researchers thought about representation learning, toying with objectives instead of architectures

* (47:40) The Restricted Boltzmann Forest

* (50:45) Imposing structure for tractable learning of distributions

* (53:11) 2011-2016 at U Sherbooke (and Twitter)

* (53:45) How Prof. Larochelle approached research problems

* (56:00) How Domain Adversarial Networks came about

* (57:12) Can we still learn from Restricted Boltzmann Machines?

* (1:02:20) The ~ Infinite ~ Restricted Boltzmann Machine

* (1:06:55) The need for researchers doing different sorts of work

* (1:08:58) 2017-present, at MILA (and Google)

* (1:09:30) Modulating Early Visual Processing by Language, neuroscientific inspiration

* (1:13:22) Representation learning and generalization, what is a good representation (Meta-Dataset, Universal representation transformer layer, universal template, Head2Toe)

* (1:15:10) Meta-Dataset motivation

* (1:18:00) Shifting focus to the problem—good practices for “recycling deep learning”

* (1:19:15) Head2Toe intuitions

* (1:21:40) What are “universal representations” and manifold perspective on datasets, what is the right pretraining dataset

* (1:26:02) Prof. Larochelle’s takeaways from Fortuitous Forgetting in Connectionist Networks (led by Hattie Zhou)

* (1:32:15) Obligatory commentary on The Present Moment and current directions in ML

* (1:36:18) The creation and motivations of the TMLR journal

* (1:41:48) Prof. Larochelle’s takeaways about doing good science, building research groups, and nurturing a research environment

* (1:44:05) Prof. Larochelle’s advice for aspiring researchers today

* (1:47:41) Outro

Links:

* Professor Larochelle’s homepage and Twitter