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

Aliya Affdal

Collaborateur·rice de recherche - UdeM

aliya.affdal@mila.quebec

Benjamin Alsbury-Nealy

Doctorat - McGill

benjamin@silicolabs.ca

antoine.boudreau-leblanc@mila.quebec

Antoine Boudreau LeBlanc

Postdoctorat - McGill

Colin Bredenberg

Visiteur de recherche indépendant - UdeM

Superviseur⋅e principal⋅e :

colin.bredenberg@mila.quebec

Nour Chahine

Doctorat - McGill

nour.chahine@mila.quebec

erica.cianfarano@mila.quebec

Raymond Chua

Doctorat - McGill

Superviseur⋅e principal⋅e :

Doctorat - McGill

Jonathan Cornford

Collaborateur·rice de recherche - McGill

cornforj@mila.quebec

Sabrina Du

Baccalauréat - McGill

sabrina.du@mila.quebec

aleksei.efremov@mail.mcgill.ca

Alex Efremov

Doctorat - McGill

Tom George

Postdoctorat - McGill

Co-superviseur⋅e :

tomgeorge1@btinternet.com

Visiteur de recherche indépendant - UdeM

oumayma.gharbi@mila.quebec

Arna Ghosh

Collaborateur·rice de recherche - McGill

Adel Halawa

Doctorat - McGill

adel.halawa@mila.quebec

Roy Henha Eyono

Doctorat - McGill

roy.eyono@mila.quebec

Sonia Joseph

Doctorat - McGill

sonia.joseph@mila.quebec

daniel.levenstein@mila.quebec

Daniel Levenstein

Collaborateur·rice alumni - McGill

Pingsheng Li

Doctorat - McGill

Co-superviseur⋅e :

pingsheng.li@mila.quebec

matthew.loukine@mail.mcgill.ca

Matthew Loukine

Doctorat - McGill

Dane Malenfant

Maîtrise recherche - McGill

dane.malenfant@mila.quebec

Abdel Mfougouon Njupoun

Doctorat - UdeM

Superviseur⋅e principal⋅e :

le-thuy-duong.nguyen@mila.quebec

abdelnjupoun@gmail.com

Maîtrise recherche - McGill

Superviseur⋅e principal⋅e :

Matt Perich

qazaleh.ranjbaran@gmail.com

Ghazaleh Ranjbaran

Visiteur de recherche indépendant - Université de Montréal

Alexis Roger

Doctorat - McGill

Co-superviseur⋅e :

Irina Rish

alexis.roger@mila.quebec

ali.sahebpasand@mila.quebec

Ali Saheb Pasand

Doctorat - McGill

Co-superviseur⋅e :

Pablo Samuel Castro

Mandana Samiei

Doctorat - McGill

Superviseur⋅e principal⋅e :

Doina Precup

samiemandana@gmail.com

Aidan Sirbu

Doctorat - McGill

aidan.sirbu@mila.quebec

hiroyuki.tanabe@mila.quebec

Hiro Tanabe

Visiteur de recherche indépendant - NA

Josh Tindall

Collaborateur·rice alumni - McGill

joshua.tindall@mila.quebec

Mashbayar Tugsbayar

Doctorat - McGill

charlotte.volk@mila.quebec

Charlotte Volk

Doctorat - McGill

Co-superviseur⋅e :

Shahab Bakhtiari

maren.wehrheim@mila.quebec

Maren Wehrheim

Visiteur de recherche indépendant - York University

amirhossein.zamani@mila.quebec

Amirhossein Zamani

Doctorat - Concordia

Superviseur⋅e principal⋅e :

Eugene Belilovsky

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

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

BrainWideBench: Benchmarking large-scale pretraining and across-animal transfer in multi-region neural recordings

Alexandre Andre

Shivashriganesh P. Mahato

Vinam Arora

Keshav Balaji

Divyansha Lachi

Nanda H. Krishna

Jingyun Xiao

Yizi Zhang

Ximeng Mao

Wenrui Ma

Han Yu

International Brain Laboratory

Daniel Birman

Niccolò Bonacchi

Gaelle A. Chapuis

Joana A. Catarino

Felicia Davatolhagh

Mayo Faulkner

Laura Freitas-Silva

Fei Hu … (voir 22 de plus)

Julia M. Huntenburg

Anup Khanal

Inês Laranjeira

Petrina Lau

Guido T. Meijer

Nathaniel J. Miska

Jean-Paul Noel

Alejandro Pan-Vazquez

Georg Raiser

Cyrille Rossant

Karolina Z. Socha

Anne E. Urai

Miles J. Wells

Steven J. West

Olivier Winter

Cole Hurwitz

Mehdi Azabou

Matthew R. Whiteway

Liam Paninski

Eva L. Dyer

Advances in large-scale neural recording have made it possible to collect data across many animals and distributed brain regions, raising th… (voir plus)e question of whether this scale can be exploited to learn general-purpose neural representations transferable across diverse downstream tasks. Yet, progress toward this goal has been limited by fragmented evaluation protocols and a narrow focus on individual task domains. Here, we present BrainWideBench, a benchmark for evaluating across-animal transfer on multi-region neural recordings, built on the International Brain Laboratory Brainwide Map dataset of neural and behavioral recordings spanning 276 brain regions from 139 mice performing a sensory-guided decision-making task. The benchmark is organized around three complementary task suites that evaluate whether learned representations support downstream decoding of behavior, can predict masked or future neural activity, and can recover biologically meaningful anatomical organization. With this benchmark, we systematically evaluate pretraining methods across transfer settings, including finetuning on downstream objectives and zero-shot generalization to unseen animals. Our results confirm pretraining improves performance over matched single-session baselines, but we show current methods exhibit heterogeneity in transfer capabilities: gains depend strongly on the alignment between pretraining objectives and downstream tasks. No single approach performs uniformly well across all three suites, and most methods are designed to only address a subset of them. Together, these findings suggest that learning representations that jointly generalize across behavior, dynamics, and anatomy remains an open challenge. By providing a unified and reproducible evaluation suite, BrainWideBench establishes a framework for measuring progress toward general-purpose models of the mouse brain.

2026-09-17

arXiv (prépublication)

arxiv.org

Top-down feedback in deep neural networks leads to functional differences during audiovisual integration

Artificial neural networks (ANNs) are an important tool for studying neural computation, but many features of the brain are not captured by … (voir plus)standard ANN architectures. One notable missing feature in most ANN models is top-down feedback, that is projections from higher-order layers to lower-order layers in the network. Top-down feedback is ubiquitous in the brain, and it has a unique modulatory impact on activity in neocortical pyramidal neurons. However, we still do not understand its computational role. Here, we develop a deep neural network model that captures the core functional properties of top-down feedback in the neocortex, allowing us to construct hierarchical recurrent ANN models that more closely reflect the architecture of the brain. We use this to explore the impact of different hierarchical recurrent architectures on an audiovisual integration task. We find that certain hierarchies, namely those that mimic the architecture of the human brain, impart ANN models with a light visual bias similar to that seen in humans. This bias does not impair performance on the audiovisual tasks. The results further suggest that different configurations of top-down feedback make otherwise identically connected models functionally distinct from each other, and from traditional feedforward and laterally recurrent models. Altogether, our findings demonstrate that modulatory top-down feedback is a computationally relevant feature of biological brains, and that incorporating it into ANNs affects their behavior and constrains the solutions it is likely to discover.

2026-08-25

eLife (publié)

A game theory for foundation models shows new paths to rational cooperation through similarity inference

Alexander Meulemans

Maciej Wołczyk

Marissa A. Weis

Rajai Nasser

Roberta Rocca

Seijin Kobayashi

Angelika Steger

Marcus Hutter

James Manyika

Rif A. Saurous

João Sacramento

Blaise Agüera y Arcas

As autonomous agents powered by foundation models are increasingly integrated into social and economic systems, understanding the principles… (voir plus) governing their collective behavior is essential for ensuring safety and cooperation. Classical game theory, the dominant framework for modeling rational interaction, is built upon the assumption of `decoupled agency,'where agents treat their own decision-making as independent of the environment and other actors. Modern AI agents, however, jointly predict their own future actions alongside external observations. Here, we report a striking finding: when interacting in stylized social dilemmas, foundation model agents engaging in optimal planning consistently converge to stable cooperation, directly contradicting classical game-theoretic predictions of mutual defection. To understand this phenomenon, we introduce the `embedded Bayesian agent,'a theoretical model for foundation model agents. By shifting from decoupled to embedded agency, these agents model themselves as part of the universe they inhabit, maintaining epistemic uncertainty about their own decision-making algorithms. We show that by inferring whether others are behaviorally similar, an embedded agent treats its own deliberation during planning as evidence: a decision to cooperate predicts a similar decision by a similar partner. We formalize this mechanism of similarity inference through the `embedded equilibrium,'a novel solution concept replacing the Nash equilibrium to provide a foundational game theory for the social behavior of modern AI agents.

2026-08-03

arXiv (prépublication)

arxiv.org

Looking to the brain to improve energy efficiency of AI

Megan A.K. Peters

Seng Bum Michael Yoo

Michał Klincewicz

Taro Toyoizumi

Taylor Webb

Hakwan Lau

2026-06-30

Current Biology (publié)

Balancing Plasticity and Stability with Fast and Slow Successor Features

Raymond Chua

Doina Precup

A hallmark of intelligence is the ability to adapt in non-stationary environments, yet deep Reinforcement Learning (RL) agents often struggl… (voir plus)e in such settings. Prior studies introduce non-stationarity through abrupt shifts in features or dynamics, whereas real-world environments often evolve gradually through continual drift. This distinction has important implications for the ``stability-plasticity dilemma'' in RL, as abrupt task changes may demand more plasticity than naturalistic settings. To address this, we modify existing 3D Miniworld and MuJoCo environments to incorporate naturalistic, continual non-stationarity, and use them to examine how stability and adaptation affect performance under continuous environmental change. We find that methods favoring stability, such as synaptic consolidation, outperform approaches focused on plasticity, such as parameters resetting. Motivated by this result, and prior evidence that Successor Features (SFs) reduce interference, we investigate whether SFs are better consolidation targets than Q-values. Across both environments, applying neuro-inspired synaptic consolidation to SFs yields superior performance on continually changing settings. Moreover, consolidation is most effective when SFs are stabilized across multiple timescales, which capture complementary aspects of gradual environmental change. Together, these results suggest that stability is more critical in continual learning when changes are gradual, and that multi-timescale consolidation of predictive representations is an effective approach.

2026-04-29

International Conference on Machine Learning (accepté)

openreview.net

Modeling the hallucinatory effects of classical psychedelics in terms of replay-dependent plasticity mechanisms

Classical psychedelics induce complex visual hallucinations in humans, generating percepts that are coherent at a low level, but which have … (voir plus)surreal, dream-like qualities at a high level. While there are many hypotheses as to how classical psychedelics could induce these effects, there are no concrete mechanistic models that capture the variety of observed effects in humans, while remaining consistent with the known pharmacological effects of classical psychedelics on neural circuits. In this work, we propose the ‘oneirogen hypothesis,’ which posits that the perceptual effects of classical psychedelics are a result of their pharmacological actions inducing neural activity states that truly are more similar to dream-like states. We simulate classical psychedelics’ effects via manipulating neural network models trained on perceptual tasks with the Wake-Sleep algorithm. This established machine learning algorithm leverages two activity phases: a perceptual phase (wake) where sensory inputs are encoded, and a generative phase (dream) where the network internally generates activity consistent with stimulus-evoked responses. We simulate the action of psychedelics by partially shifting the model to the ‘Sleep’ state, which entails a greater influence of top-down connections, in line with the impact of psychedelics on apical dendrites. The effects resulting from this manipulation capture a number of experimentally observed phenomena, including the emergence of hallucinations, increases in stimulus-conditioned variability, and large increases in synaptic plasticity. We further provide a number of testable predictions which could be used to validate or invalidate our oneirogen hypothesis.

2026-04-20

eLife (publié)

The oneirogen hypothesis: modeling the hallucinatory effects of classical psychedelics in terms of replay-dependent plasticity mechanisms

Abstract Classical psychedelics induce complex visual hallucinations in humans, generating percepts that are co-herent at a … (voir plus)low level, but which have surreal, dream-like qualities at a high level. While there are many hypotheses as to how classical psychedelics could induce these effects, there are no concrete mechanistic models that capture the variety of observed effects in humans, while remaining consistent with the known pharmacological effects of classical psychedelics on neural circuits. In this work, we propose the “oneirogen hypothesis”, which posits that the perceptual effects of classical psychedelics are a result of their pharmacological actions inducing neural activity states that truly are more similar to dream-like states. We simulate classical psychedelics’ effects via manipulating neural network models trained on perceptual tasks with the Wake-Sleep algorithm. This established machine learning algorithm leverages two activity phases, a perceptual phase (wake) where sensory inputs are encoded, and a generative phase (dream) where the network internally generates activity consistent with stimulus-evoked responses. We simulate the action of psychedelics by partially shifting the model to the ‘Sleep’ state, which entails a greater influence of top-down connections, in line with the impact of psychedelics on apical dendrites. The effects resulting from this manipulation capture a number of experimentally observed phenomena including the emergence of hallucinations, increases in stimulus-conditioned variability, and large increases in synaptic plasticity. We further provide a number of testable predictions which could be used to validate or invalidate our oneirogen hypothesis.

2026-01-12

eLife (accepté)

Interpreting Physics in Video World Models

Sonia Joseph

Quentin Garrido

Randall Balestriero

Matthew Kowal

Thomas Fel

Shahab Bakhtiari

Mike Rabbat

A long-standing question in physical reasoning is whether video-based models need to rely on factorized representations of physical variable… (voir plus)s in order to make physically accurate predictions, or whether they can implicitly represent such variables in a distributed manner. While modern video world models achieve strong performance on intuitive physics benchmarks, it remains unclear which of these representational regimes they implement internally. Here, we present the first interpretability study to directly examine physical representations inside large-scale video encoders. Using layerwise probing, subspace geometry, patch-level decoding, and targeted attention ablations, we characterize where physical information becomes accessible and how it is organized within encoder-based video transformers. Across architectures, we identify a sharp intermediate-depth transition— which we call the \emph{Physics Emergence Zone}—at which physical variables become accessible. Physics-related representations peak shortly after this transition and degrade toward the output layers. Decomposing motion into explicit variables, we find that scalar quantities such as speed and acceleration are available from early layers onwards, whereas motion direction becomes accessible only at the Physics Emergence Zone. Notably, we find that direction is encoded through a high-dimensional population structure with circular geometry, requiring coordinated multi-feature intervention to control. These findings suggest that modern video models do not use factorized representations of physical variables like a classical physics engine. Instead, they use a distributed representation that is nonetheless sufficient for making physical predictions.

2025-12-31

International Conference on Machine Learning (Accept (regular))

openreview.net

RetINaBox: A hands-on learning tool for experimental neuroscience

Brune Bettler

Flavia Arias Armas

Erica Cianfarano

Vanessa Bordonaro

Megan Liu

Matthew Loukine

Mingyu Wan

Aude Villemain

Stuart Trenholm

An exciting aspect of neuroscience is developing and testing hypotheses via experimentation. However, due to logistical and financial hurdle… (voir plus)s, the experiment and discovery component of neuroscience is generally lacking in classroom and outreach settings. To address this issue, here we introduce RetINaBox: a low-cost open-source electronic visual system simulator that provides users with a hands-on tool to discover how the visual system builds feature detectors. RetINaBox features an LED array for generating visual stimuli and a photodiode array that acts as a mosaic of model photoreceptors. Custom software on a Raspberry Pi computer reads out responses from model photoreceptors and allows users to control the polarity and delay of the signal transfer from model photoreceptors to model retinal ganglion cells. Interactive lesson plans are provided, guiding users to discover different types of visual feature detectors—including ON/OFF, center-surround, orientation selective, and direction selective receptive fields—as well as their underlying circuit computations.

2025-12-31

eNeuro (publié)

Know Thyself by Knowing Others: Learning Neuron Identity from Population Context

Vinam Arora

Divyansha Lachi

Ian J. Knight

Mehdi Azabou

Cole Hurwitz

Joshua H. Siegle

Eva L. Dyer

Identifying the functional identity of individual neurons is essential for interpreting circuit dynamics, yet it remains a major challenge i… (voir plus)n large-scale _in vivo_ recordings where anatomical and molecular labels are often unavailable. Here we introduce NuCLR, a self-supervised framework that learns context-aware representations of neuron identity by modeling each neuron's role within the broader population. NuCLR employs a spatio-temporal transformer that captures both within-neuron dynamics and across-neuron interactions. It is trained with a sample-wise contrastive objective that encourages temporally-stable and discriminative embeddings. Across multiple open-access datasets, NuCLR outperforms prior methods in both cell type and brain region classification. Critically, it exhibits strong zero-shot generalization to entirely new populations, without any retraining or access to stimulus labels. Furthermore, we demonstrate that our framework scales effectively with data size. Overall, our results demonstrate that modeling population context is crucial for understanding neuron identity and that rich signal for cell-typing and neuron localization is present in neural activity alone.Code available at: https://github.com/nerdslab/nuclr.

2025-12-02

NEURIPS (Accept (poster))

openreview.net

Top-down feedback matters: Functional impact of brainlike connectivity motifs on audiovisual integration

Mashbayar Tugsbayar

Mingze Li

Eilif B Muller

Artificial neural networks (ANNs) are an important tool for studying neural computation, but many features of the brain are not captured by … (voir plus)standard ANN architectures. One notable missing feature in most ANN models is top-down feedback, i.e. projections from higher-order layers to lower-order layers in the network. Top-down feedback is ubiquitous in the brain, and it has a unique modulatory impact on activity in neocortical pyramidal neurons. However, we still do not understand its computational role. Here we develop a deep neural network model that captures the core functional properties of top-down feedback in the neocortex, allowing us to construct hierarchical recurrent ANN models that more closely reflect the architecture of the brain. We use this to explore the impact of different hierarchical recurrent architectures on an audiovisual integration task. We find that certain hierarchies, namely those that mimic the architecture of the human brain, impart ANN models with a light visual bias similar to that seen in humans. This bias does not impair performance on the audiovisual tasks. The results further suggest that different configurations of top-down feedback make otherwise identically connected models functionally distinct from each other, and from traditional feedforward and laterally recurrent models. Altogether our findings demonstrate that modulatory top-down feedback is a computationally relevant feature of biological brains, and that incorporating it into ANNs affects their behavior and constrains the solutions it’s likely to discover.

2025-11-09

bioRxiv (prépublication)

Learning to combine top-down context and feed-forward representations under ambiguity with apical and basal dendrites

Guillaume Etter

Busra Tugce Gurbuz

One of the hallmark features of neocortical anatomy is the presence of extensive top-down projections into primary sensory areas, with many … (voir plus)impinging on the distal apical dendrites of pyramidal neurons. While it is known that they exert a modulatory effect, altering the gain of responses, their functional role remains an active area of research. It is hypothesized that these top-down projections carry contextual information that can help animals to resolve ambiguities in sensory data. One proposed mechanism of contextual integration is a non-linear integration of distinct input streams at apical and basal dendrites of pyramidal neurons. Computationally, however, it is yet to be demonstrated how such an architecture could leverage distinct compartments for flexible contextual integration and sensory processing when both sensory and context signals can be unreliable. Here, we implement an augmented deep neural network with distinct apical and basal compartments that integrates a) contextual information from top-down projections to apical compartments, and b) sensory representations driven by bottom-up projections to basal compartments, via a biophysically inspired rule. In addition, we develop a new multi-scenario contextual integration task using a generative image modeling approach. In addition to generalizing previous contextual integration tasks, it better captures the diversity of scenarios where neither contextual nor sensory information are fully reliable. To solve this task, this model successfully learns to select among integration strategies. We find that our model outperforms those without the "apical prior" when contextual information contradicts sensory input. Altogether, this suggests that the apical prior and biophysically inspired integration rule could be key components necessary for handling the ambiguities that animals encounter in the diverse contexts of the real world.

2025-06-22

Cerebral Cortex (New York, NY) (publié)