Portrait de Blake Richards

Blake Richards

Membre académique principal

blake.richards@mila.quebec

Chaire en IA Canada-CIFAR

Professeur adjoint, McGill University, École d'informatique et Département de neurologie et de neurochirurgie

Biographie

Blake Richards est professeur agrégé à l'École d'informatique et au Département de neurologie et de neurochirurgie de l'Université McGill et membre du corps professoral de Mila – Institut québécois d’intelligence artificielle. Ses recherches se situent à l'intersection des neurosciences et de l'intelligence artificielle. Son laboratoire étudie les principes universels de l'intelligence qui s'appliquent aux agents naturels et artificiels. Il a reçu plusieurs distinctions pour ses travaux, notamment une bourse Arthur-B.-McDonald du Conseil de recherches en sciences naturelles et en génie du Canada (CRSNG) en 2022, le Prix du jeune chercheur de l'Association canadienne des neurosciences en 2019 et une chaire en IA Canada-CIFAR en 2018. M. Richards a en outre été titulaire d'une bourse postdoctorale Banting à l'hôpital SickKids de 2011 à 2013. Il a obtenu un doctorat en neurosciences de l'Université d'Oxford en 2010 et une licence en sciences cognitives et en IA de l'Université de Toronto en 2004.

Étudiants actuels

Adrien Peyrache

Visiteur de recherche indépendant

adrien.peyrache@mila.quebec

Doctorat - McGill University

aleksei.efremov@mila.quebec

Ali Saheb Pasand

Doctorat - McGill University

Superviseur⋅e principal⋅e :

ali.sahebpasand@mila.quebec

Alissia Di Maria

Stagiaire de recherche - McGill University

alissia.dimaria@mila.quebec

Collaborateur·rice alumni

zixiang.huang@mila.quebec

Doctorat - McGill University

ghosharn@mila.quebec

Postdoctorat - Université de Montréal

Superviseur⋅e principal⋅e :

chen.sun@mila.quebec

Colin Bredenberg

Postdoctorat - Université de Montréal

Superviseur⋅e principal⋅e :

Guillaume Lajoie

colin.bredenberg@mila.quebec

Maîtrise recherche - McGill University

dane.malenfant@mila.quebec

Daniel Levenstein

Postdoctorat - McGill University

daniel.levenstein@mila.quebec

Divyansha Lachi

Collaborateur·rice de recherche - Georgia Tech

divyansha.lachi@mila.quebec

Doctorat - McGill University

lindongy@mila.quebec

Erica Cianfarano

Doctorat - McGill University

erica.cianfarano@mila.quebec

Ethan Caballero

Doctorat - McGill University

Co-superviseur⋅e :

ethan.caballero@mila.quebec

Etienne Barou-Laforie

Stagiaire de recherche - McGill University

etienne.barou-laforie@mila.quebec

Jonathan Cornford

Postdoctorat - McGill University

cornforj@mila.quebec

Maîtrise recherche - McGill University

joshua.tindall@mila.quebec

Doctorat - McGill University

Superviseur⋅e principal⋅e :

samieima@mila.quebec

Mashbayar Tugsbayar

Doctorat - McGill University

Mohammad Yaghoubi

Doctorat - McGill University

yaghoubm@mila.quebec

Postdoctorat - McGill University

j.quinn.lee@mila.quebec

Doctorat - McGill University

Superviseur⋅e principal⋅e :

chuaraym@mila.quebec

Postdoctorat - McGill University

Co-superviseur⋅e :

Guillaume Lajoie

Roman.Pogodin@mila.Quebec

Roy Henha Eyono

Doctorat - McGill University

roy.eyono@mila.quebec

Santiago Jaramillo

Visiteur de recherche indépendant - University of Oregon

santiago.jaramillo@mila.quebec

Doctorat - McGill University

sonia.joseph@mila.quebec

Collaborateur·rice alumni

penmetss@mila.quebec

Stagiaire de recherche - University of Oslo

vemund.schoyen@mila.quebec

Maîtrise recherche - McGill University

xuejing.pan@mila.quebec

Billets de blogue

Visuel abstrait

13 juin 2024

Que nous apprennent les distributions des coefficients synaptiques au sujet de l’apprentissage dans le cerveau ?

par

Jonathan Cornford

Arna Ghosh

Guillaume Lajoie

α-ReQ: Assessing Representation Quality in SSL

29 août 2023

α-ReQ : Évaluation de la qualité des représentations en apprentissage auto-supervisé

par

KK Agrawal

Arnab Kumar-Mondal

Arna Ghosh

Blake A. Richards

Publications

Irrelevance by inhibition: Learning, computation, and implications for schizophrenia

Nathan Insel

Jordan Guerguiev

Symptoms of schizophrenia may arise from a failure of cortical circuits to filter-out irrelevant inputs. Schizophrenia has also been linked … (voir plus)to disruptions in cortical inhibitory interneurons, consistent with the possibility that in the normally functioning brain, these cells are in some part responsible for determining which sensory inputs are relevant versus irrelevant. Here, we develop a neural network model that demonstrates how the cortex may learn to ignore irrelevant inputs through plasticity processes affecting inhibition. The model is based on the proposal that the amount of excitatory output from a cortical circuit encodes the expected magnitude of reward or punishment (“relevance”), which can be trained using a temporal difference learning mechanism acting on feedforward inputs to inhibitory interneurons. In the model, irrelevant and blocked stimuli drive lower levels of excitatory activity compared with novel and relevant stimuli, and this difference in activity levels is lost following disruptions to inhibitory units. When excitatory units are connected to a competitive-learning output layer with a threshold, the relevance code can be shown to “gate” both learning and behavioral responses to irrelevant stimuli. Accordingly, the combined network is capable of recapitulating published experimental data linking inhibition in frontal cortex with fear learning and expression. Finally, the model demonstrates how relevance learning can take place in parallel with other types of learning, through plasticity rules involving inhibitory and excitatory components, respectively. Altogether, this work offers a theory of how the cortex learns to selectively inhibit inputs, providing insight into how relevance-assignment problems may emerge in schizophrenia.

2018-08-01

PLoS Comput. Biol. (publié)

Assessing the Scalability of Biologically-Motivated Deep Learning Algorithms and Architectures

Sergey Bartunov

Adam Santoro

Luke Marris

Geoffrey Hinton

Timothy P. Lillicrap

The backpropagation of error algorithm (BP) is impossible to implement in a real brain. The recent success of deep networks in machine learn… (voir plus)ing and AI, however, has inspired proposals for understanding how the brain might learn across multiple layers, and hence how it might approximate BP. As of yet, none of these proposals have been rigorously evaluated on tasks where BP-guided deep learning has proved critical, or in architectures more structured than simple fully-connected networks. Here we present results on scaling up biologically motivated models of deep learning on datasets which need deep networks with appropriate architectures to achieve good performance. We present results on the MNIST, CIFAR-10, and ImageNet datasets and explore variants of target-propagation (TP) and feedback alignment (FA) algorithms, and explore performance in both fully- and locally-connected architectures. We also introduce weight-transport-free variants of difference target propagation (DTP) modified to remove backpropagation from the penultimate layer. Many of these algorithms perform well for MNIST, but for CIFAR and ImageNet we find that TP and FA variants perform significantly worse than BP, especially for networks composed of locally connected units, opening questions about whether new architectures and algorithms are required to scale these approaches. Our results and implementation details help establish baselines for biologically motivated deep learning schemes going forward.