Blake Richards

Biographie

Blake Richards est directeur de recherche au sein de l'équipe Paradigms of Intelligence chez Google et professeur agrégé à l'École d'informatique et au Département de neurologie et de neurochirurgie de l'Université McGill. Il est également et membre académique principal à 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

Benjamin Alsbury-Nealy

Doctorat - McGill

Antoine Boudreau LeBlanc

Postdoctorat - McGill

Colin Bredenberg

Postdoctorat - UdeM

Superviseur⋅e principal⋅e :

Guillaume Lajoie

Ethan Caballero

Doctorat - McGill

Co-superviseur⋅e :

Doctorat - McGill

Visiteur de recherche indépendant - NYU

Doctorat - McGill

Superviseur⋅e principal⋅e :

Doctorat - McGill

Collaborateur·rice alumni - McGill

Sabrina Du

Baccalauréat - McGill

Doctorat - McGill

Tom George

Postdoctorat - McGill

Co-superviseur⋅e :

Visiteur de recherche indépendant - UdeM

Arna Ghosh

Collaborateur·rice alumni - McGill

Adel Halawa

Doctorat - McGill

Doctorat - McGill

Doctorat - McGill

Postdoctorat - McGill

Doctorat - McGill

Doctorat - McGill

Doctorat - McGill

Abdel Mfougouon Njupoun

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Collaborateur·rice alumni - McGill

Ghazaleh Ranjbaran

Visiteur de recherche indépendant - Université de Montréal

Alexis Roger

Doctorat - McGill

Co-superviseur⋅e :

Irina Rish

Ali Saheb Pasand

Doctorat - McGill

Co-superviseur⋅e :

Pablo Samuel Castro

Mandana Samiei

Doctorat - McGill

Superviseur⋅e principal⋅e :

Aidan Sirbu

Maîtrise recherche - McGill

Hiro Tanabe

Visiteur de recherche indépendant - NA

Josh Tindall

Maîtrise recherche - McGill

Mashbayar Tugsbayar

Doctorat - McGill

Charlotte Volk

Maîtrise recherche - McGill

Co-superviseur⋅e :

Shahab Bakhtiari

Maren Wehrheim

Visiteur de recherche indépendant - York University

Apprentissage automatique pour la segmentation des différentes activations des fibres nerveuses à partir des signaux neuronaux du cerveau vers le corps

AmirHossein Zamani

Doctorat - Concordia

Superviseur⋅e principal⋅e :

Billets de blogue

Représentation graphique d'un nerf vague

21 mai 2025

par

Param Raval

Olivier Tessier-Larivière

Pascal Fortier-Poisson

Blake Richards

Guillaume Lajoie

Lire l'article

13 juin 2024

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

par

Roman Pogodin

Jonathan Cornford

Arna Ghosh

Gauthier Gidel

Guillaume Lajoie

Blake Richards

Lire l'article

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

Lire l'article

Publications

The Brain-Computer Metaphor Debate Is Useless: A Matter of Semantics

Timothy P. Lillicrap

2022-02-08

Frontiers in Computer Science (publié)

A Generalized Bootstrap Target for Value-Learning, Efficiently Combining Value and Feature Predictions

Anthony GX-Chen

Veronica Chelu

Joelle Pineau

Estimating value functions is a core component of reinforcement learning algorithms. Temporal difference (TD) learning algorithms use bootst… (voir plus)rapping, i.e. they update the value function toward a learning target using value estimates at subsequent time-steps. Alternatively, the value function can be updated toward a learning target constructed by separately predicting successor features (SF)—a policy-dependent model—and linearly combining them with instantaneous rewards. We focus on bootstrapping targets used when estimating value functions, and propose a new backup target, the ?-return mixture, which implicitly combines value-predictive knowledge (used by TD methods) with (successor) feature-predictive knowledge—with a parameter ? capturing how much to rely on each. We illustrate that incorporating predictive knowledge through an ??-discounted SF model makes more efficient use of sampled experience, compared to either extreme, i.e. bootstrapping entirely on the value function estimate, or bootstrapping on the product of separately estimated successor features and instantaneous reward models. We empirically show this approach leads to faster policy evaluation and better control performance, for tabular and nonlinear function approximations, indicating scalability and generality.

2022-01-05

ArXiv (preprint)

arxiv.org

$\alpha$-ReQ : Assessing Representation Quality in Self-Supervised Learning by measuring eigenspectrum decay

Kumar Krishna Agrawal

Arnab Kumar Mondal

Arna Ghosh

Self-Supervised Learning (SSL) with large-scale unlabelled datasets enables learning useful representations for multiple downstream tasks. H… (voir plus)owever, assessing the quality of such representations efficiently poses nontrivial challenges. Existing approaches train linear probes (with frozen features) to evaluate performance on a given task. This is expensive both computationally, since it requires retraining a new prediction head for each downstream task, and statistically, requires task-specific labels for multiple tasks. This poses a natural question, how do we efficiently determine the "goodness" of representations learned with SSL across a wide range of potential downstream tasks? In particular, a task-agnostic statistical measure of representation quality, that predicts generalization without explicit downstream task evaluation, would be highly desirable. In this work, we analyze characteristics of learned representations

openreview.net

Beyond accuracy: generalization properties of bio-plausible temporal credit assignment rules

Yuhan Helena Liu

Eric Todd SheaBrown

Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution

Anthony Zador

Bence Ölveczky

Sean Escola

Yoshua Bengio

Kwabena Boahen

Matthew Botvinick

Dmitri Chklovskii

Anne Churchland

Claudia Clopath

James DiCarlo

Surya Ganguli

Jeff Hawkins

Konrad Paul Kording

Alexei Koulakov

Yann Lecun

Timothy P. Lillicrap

Adam Marblestone

Bruno Olshausen

Alexandre Pouget … (voir 7 de plus)

Cristina Savin

Terrence Sejnowski

Eero Simoncelli

Sara Solla

David Sussillo

Andreas S. Tolias

Doris Tsao

2022-01-01

arXiv.org (prépublication)

Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution

Anthony Zador

Bence Ölveczky

Sean Escola

Yoshua Bengio

Kwabena Boahen

Matthew Botvinick

Dmitri Chklovskii

Anne Churchland

Claudia Clopath

James DiCarlo

Surya Ganguli

Jeff Hawkins

Konrad Paul Kording

Alexei Koulakov

Yann Lecun

Timothy P. Lillicrap

Adam Marblestone

Bruno Olshausen

Alexandre Pouget … (voir 7 de plus)

Cristina Savin

Terrence Sejnowski

Eero Simoncelli

Sara Solla

David Sussillo

Andreas S. Tolias

Doris Tsao

2022-01-01

arXiv.org (prépublication)

The functional specialization of visual cortex emerges from training parallel pathways with self-supervised predictive learning

Shahab Bakhtiari

Patrick J Mineault

Timothy P. Lillicrap

Christopher C. Pack

The visual system of mammals is comprised of parallel, hierarchical specialized pathways. Different pathways are specialized in so far as th… (voir plus)ey use representations that are more suitable for supporting specific downstream behaviours. In particular, the clearest example is the specialization of the ventral (“what”) and dorsal (“where”) pathways of the visual cortex. These two pathways support behaviours related to visual recognition and movement, respectively. To-date, deep neural networks have mostly been used as models of the ventral, recognition pathway. However, it is unknown whether both pathways can be modelled with a single deep ANN. Here, we ask whether a single model with a single loss function can capture the properties of both the ventral and the dorsal pathways. We explore this question using data from mice, who like other mammals, have specialized pathways that appear to support recognition and movement behaviours. We show that when we train a deep neural network architecture with two parallel pathways using a self-supervised predictive loss function, we can outperform other models in fitting mouse visual cortex. Moreover, we can model both the dorsal and ventral pathways. These results demonstrate that a self-supervised predictive learning approach applied to parallel pathway architectures can account for some of the functional specialization seen in mammalian visual systems.

openreview.net

From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence

Nicholas Roy

Ingmar Posner

T. Barfoot

Philippe Beaudoin

Yoshua Bengio

Jeannette Bohg

Oliver Brock

Isabelle Depatie

Dieter Fox

D. Koditschek

Tom'as Lozano-p'erez

Vikash K. Mansinghka

Chris Pal

Dorsa Sadigh

Stefan Schaal

G. Sukhatme

Denis Therien

Marc Emile Toussaint

Michiel van de Panne

2021-10-28

ArXiv (prépublication)

arxiv.org

Promoting and Optimizing the Use of 3D-Printed Objects in Spontaneous Recognition Memory Tasks in Rodents: A Method for Improving Rigor and Reproducibility

Mehreen Inayat

Arely Cruz-Sanchez

Hayley H. A. Thorpe

Jude A. Frie

Jibran Y. Khokhar

Maithe Arruda-Carvalho

2021-09-01

eNeuro (publié)

Forgetting Enhances Episodic Control With Structured Memories

Annik Yalnizyan-carson

Forgetting is a normal process in healthy brains, and evidence suggests that the mammalian brain forgets more than is required based on limi… (voir plus)tations of mnemonic capacity. Episodic memories, in particular, are liable to be forgotten over time. Researchers have hypothesized that it may be beneficial for decision making to forget episodic memories over time. Reinforcement learning offers a normative framework in which to test such hypotheses. Here, we show that a reinforcement learning agent that uses an episodic memory cache to find rewards in maze environments can forget a large percentage of older memories without any performance impairments, if they utilize mnemonic representations that contain structural information about space. Moreover, we show that some forgetting can actually provide a benefit in performance compared to agents with unbounded memories. Our analyses of the agents show that forgetting reduces the influence of outdated information and states which are not frequently visited on the policies produced by the episodic control system. These results support the hypothesis that some degree of forgetting can be beneficial for decision making, which can help to explain why the brain forgets more than is required by capacity limitations.

2021-08-12

bioRxiv (preprint)

Learning function from structure in neuromorphic networks

Laura E. Suárez

Guillaume Lajoie

Bratislav Mišić

2021-08-09

Nature Machine Intelligence (publié)

Neocortical inhibitory interneuron subtypes are differentially attuned to synchrony- and rate-coded information

Luke Y. Prince

Matthew M. Tran

Dorian Grey

Lydia Saad

Helen Chasiotis

Jeehyun Kwag

Michael M Kohl

2021-08-05

Communications Biology (publié)