Blake Richards

Biography

Blake Richards is an associate professor at the School of Computer Science and in the Department of Neurology and Neurosurgery at McGill University, and a core academic member of Mila – Quebec Artificial Intelligence Institute.

Richards’ research lies at the intersection of neuroscience and AI. His laboratory investigates universal principles of intelligence that apply to both natural and artificial agents.

He has received several awards for his work, including the NSERC Arthur B. McDonald Fellowship in 2022, the Canadian Association for Neuroscience Young Investigator Award in 2019, and a Canada CIFAR AI Chair in 2018. Richards was a Banting Postdoctoral Fellow at SickKids Hospital from 2011 to 2013.

He obtained his PhD in neuroscience from the University of Oxford in 2010, and his BSc in cognitive science and AI from the University of Toronto in 2004.

Current Students

Stella Bae

Independent visiting researcher - Seoul National University

Antoine Boudreau LeBlanc

Postdoctorate - McGill University

Colin Bredenberg

Postdoctorate - Université de Montréal

Principal supervisor :

aleksei.efremov@mail.mcgill.ca

Ethan Caballero

PhD - McGill University

Co-supervisor :

PhD - McGill University

Principal supervisor :

PhD - McGill University

Jonathan Cornford

Postdoctorate - McGill University

Alex Efremov

PhD - McGill University

Arna Ghosh

PhD - McGill University

Danny Han

Independent visiting researcher - Seoul National University

Roy Henha Eyono

PhD - McGill University

Angela Hu

Research Intern - McGill University

Ann Huang

Collaborating Alumni

Sonia Joseph

PhD - McGill University

Clara Kümpel

Independent visiting researcher - ETH Zurich

Divyansha Lachi

Collaborating researcher - Georgia Tech

Postdoctorate - McGill University

zixuan.li3@mail.mcgill.ca

Zixuan Li Li

Undergraduate - McGill University

Dongyan Lin

PhD - McGill University

Master's Research - McGill University

Toky Raharison Ralambomihanta

Abdel Mfougouon Njupoun

PhD - Université de Montréal

Principal supervisor :

Undergraduate - McGill University

Xuejing Pan

Master's Research - McGill University

Adrien Peyrache

Independent visiting researcher

Roman Pogodin

Postdoctorate - McGill University

Co-supervisor :

Undergraduate - McGill University

tokiniaina.raharisonralambomihan@mail.mcgill.ca

Alexis Roger

PhD - McGill University

Co-supervisor :

Irina Rish

Ali Saheb Pasand

PhD - McGill University

Co-supervisor :

Pablo Samuel Castro

Mandana Samiei

PhD - McGill University

Principal supervisor :

Doina Precup

samiemandana@gmail.com

Aidan Sirbu

Master's Research - McGill University

Co-supervisor :

Shahab Bakhtiari

Josh Tindall

Master's Research - McGill University

Mashbayar Tugsbayar

PhD - McGill University

Charlotte Volk

Master's Research - McGill University

Co-supervisor :

Shahab Bakhtiari

Hee-Hwan Wang

Independent visiting researcher - Seoul National University

Maren Wehrheim

Independent visiting researcher - York University

Mohammad Yaghoubi

PhD - McGill University

What Do Synaptic Weight Distributions Tell Us About Learning in the Brain ?

AmirHossein Zamani

PhD - Concordia University

Principal supervisor :

Blog Posts

June 13, 2024

Roman Pogodin

Jonathan Cornford

Arna Ghosh

Gauthier Gidel

Guillaume Lajoie

Blake Richards

Read the article

August 29, 2023

α-ReQ: Assessing Representation Quality in SSL

KK Agrawal

Arnab Kumar-Mondal

Arna Ghosh

Blake A. Richards

Read the article

Publications

Brain-like learning with exponentiated gradients

Jonathan Cornford

Roman Pogodin

Arna Ghosh

Kaiwen Sheng

Brendan A. Bicknell

Olivier Codol

Beverley A. Clark

2024-10-26

bioRxiv (preprint)

Multi-agent cooperation through learning-aware policy gradients

Alexander Meulemans

Seijin Kobayashi

Johannes von Oswald

Nino Scherrer

Eric Elmoznino

Blaise Agüera y Arcas

João Sacramento

Self-interested individuals often fail to cooperate, posing a fundamental challenge for multi-agent learning. How can we achieve cooperation… (see more) among self-interested, independent learning agents? Promising recent work has shown that in certain tasks cooperation can be established between learning-aware agents who model the learning dynamics of each other. Here, we present the first unbiased, higher-derivative-free policy gradient algorithm for learning-aware reinforcement learning, which takes into account that other agents are themselves learning through trial and error based on multiple noisy trials. We then leverage efficient sequence models to condition behavior on long observation histories that contain traces of the learning dynamics of other agents. Training long-context policies with our algorithm leads to cooperative behavior and high returns on standard social dilemmas, including a challenging environment where temporally-extended action coordination is required. Finally, we derive from the iterated prisoner's dilemma a novel explanation for how and when cooperation arises among self-interested learning-aware agents.

2024-10-24

ArXiv (preprint)

arxiv.org

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

Mashbayar Tugsbayar

Mingze Li

Eilif Benjamin Muller

2024-10-03

bioRxiv (preprint)

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

Colin Bredenberg

Fabrice Normandin

2024-09-30

bioRxiv (preprint)

Harnessing small projectors and multiple views for efficient vision pretraining

Arna Ghosh

Kumar Krishna Agrawal

Shagun Sodhani

Adam M. Oberman

2024-09-25

NeurIPS.cc/2024/Conference (poster)

Learning Successor Features the Simple Way

Raymond Chua

Arna Ghosh

Christos Kaplanis

Doina Precup

In Deep Reinforcement Learning (RL), it is a challenge to learn representations that do not exhibit catastrophic forgetting or interference … (see more)in non-stationary environments. Successor Features (SFs) offer a potential solution to this challenge. However, canonical techniques for learning SFs from pixel-level observations often lead to representation collapse, wherein representations degenerate and fail to capture meaningful variations in the data. More recent methods for learning SFs can avoid representation collapse, but they often involve complex losses and multiple learning phases, reducing their efficiency. We introduce a novel, simple method for learning SFs directly from pixels. Our approach uses a combination of a Temporal-difference (TD) loss and a reward prediction loss, which together capture the basic mathematical definition of SFs. We show that our approach matches or outperforms existing SF learning techniques in both 2D (Minigrid), 3D (Miniworld) mazes and Mujoco, for both single and continual learning scenarios. As well, our technique is efficient, and can reach higher levels of performance in less time than other approaches. Our work provides a new, streamlined technique for learning SFs directly from pixel observations, with no pretraining required.

2024-09-25

NeurIPS.cc/2024/Conference (poster)

Towards a "Universal Translator" for Neural Dynamics at Single-Cell, Single-Spike Resolution

Yizi Zhang

Yanchen Wang

Donato M. Jiménez-Benetó

Zixuan Wang

Mehdi Azabou

Renee Tung

Olivier Winter

International Brain Laboratory

Eva L Dyer

Liam Paninski

Cole Lincoln Hurwitz

2024-09-25

NeurIPS.cc/2024/Conference (poster)

Stochastic Wiring of Cell Types Enhances Fitness by Generating Phenotypic Variability

Divyansha Lachi

Ann Huang

Augustine N. Mavor-Parker

Arna Ghosh

Anthony Zador

The development of neural connectivity is a crucial biological process that gives rise to diverse brain circuits and behaviors. Neural devel… (see more)opment is a stochastic process, but this stochasticity is often treated as a nuisance to overcome rather than as a functional advantage. Here we use a computational model, in which connection probabilities between discrete cell types are genetically specified, to investigate the benefits of stochasticity in the development of neural wiring. We show that this model can be viewed as a generalization of a powerful class of artificial neural networks—Bayesian neural networks—where each network parameter is a sample from a distribution. Our results reveal that stochasticity confers a greater benefit in large networks and variable environments, which may explain its role in organisms with larger brains. Surprisingly, we find that the average fitness over a population of agents is higher than a single agent defined by the average connection probability. Our model reveals how developmental stochasticity, by inducing a form of non-heritable phenotypic variability, can increase the probability that at least some individuals will survive in rapidly changing, unpredictable environments. Our results suggest how stochasticity may be an important feature rather than a bug in neural development.

2024-08-08

bioRxiv (preprint)

Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent

Karolis Jucys

George Adamopoulos

Mehrab Hamidi

Stephanie Milani

Mohammad Reza Samsami

Artem Zholus

Sonia Joseph

Irina Rish

Özgür Şimşek

Understanding the mechanisms behind decisions taken by large foundation models in sequential tasks is critical to ensuring that such systems… (see more) operate transparently and safely. However, interpretability methods have not yet been applied extensively to large-scale agents based on reinforcement learning. In this work, we perform exploratory analysis on the Video PreTraining (VPT) Minecraft playing agent, one of the largest open-source vision-based agents. We try to illuminate its reasoning mechanisms by applying various interpretability techniques. First, we analyze the attention mechanism while the agent solves its training task --- crafting a diamond pickaxe. The agent seems to pay attention to the 4 last frames and several key-frames further back. This provides clues as to how it maintains coherence in the task that takes 3-10 minutes, despite the agent's short memory span of only six seconds. Second, we perform various interventions, which help us uncover a worrying case of goal misgeneralization: VPT mistakenly identifies a villager wearing brown clothes as a tree trunk and punches it to death, when positioned stationary under green tree leaves. We demonstrate similar misbehavior in a related agent (STEVE-1), which motivates the use of VPT as a model organism for large-scale vision-based agent interpretability.

2024-06-24

ICML.cc/2024/Workshop/MI (poster)

Stimulus information guides the emergence of behavior-related signals in primary somatosensory cortex during learning.

Mariangela Panniello

Colleen J Gillon

Roberto Maffulli

Marco Celotto

Stefano Panzeri

Michael M Kohl

2024-05-25

Cell Reports (published)

Sequential predictive learning is a unifying theory for hippocampal representation and replay

Daniel Levenstein

Aleksei Efremov

Roy Henha Eyono

Adrien Peyrache

The mammalian hippocampus contains a cognitive map that represents an animal’s position in the environment 1 and generates offline “repl… (see more)ay” 2,3 for the purposes of recall 4, planning 5,6, and forming long term memories 7. Recently, it’s been found that artificial neural networks trained to predict sensory inputs develop spatially tuned cells 8, aligning with predictive theories of hippocampal function 9–11. However, whether predictive learning can also account for the ability to produce offline replay is unknown. Here, we find that spatially tuned cells, which robustly emerge from all forms of predictive learning, do not guarantee the presence of a cognitive map with the ability to generate replay. Offline simulations only emerged in networks that used recurrent connections and head-direction information to predict multi-step observation sequences, which promoted the formation of a continuous attractor reflecting the geometry of the environment. These offline trajectories were able to show wake-like statistics, autonomously replay recently experienced locations, and could be directed by a virtual head direction signal. Further, we found that networks trained to make cyclical predictions of future observation sequences were able to rapidly learn a cognitive map and produced sweeping representations of future positions reminiscent of hippocampal theta sweeps 12. These results demonstrate how hippocampal-like representation and replay can emerge in neural networks engaged in predictive learning, and suggest that hippocampal theta sequences reflect a circuit that implements a data-efficient algorithm for sequential predictive learning. Together, this framework provides a unifying theory for hippocampal functions and hippocampal-inspired approaches to artificial intelligence.

2024-04-29

bioRxiv (preprint)

Fast burst fraction transients convey information independent of the firing rate

Richard Naud

Xingyun Wang

Zachary Friedenberger

Alexandre Payeur

Jiyun N. Shin

Jean-Claude Béïque

Moritz Drüke

Matthew E. Larkum

Guy Doron

Theories of attention and learning have hypothesized a central role for high-frequency bursting in cognitive functions, but experimental rep… (see more)orts of burst-mediated representations in vivo have been limited. Here we used a novel demultiplexing approach by considering a conjunctive burst code. We studied this code in vivo while animals learned to report direct electrical stimulation of the somatosensory cortex and found two acquired yet independent representations. One code, the event rate, showed a sparse and succint stiumulus representation and a small modulation upon detection errors. The other code, the burst fraction, correlated more globally with stimulation and more promptly responded to detection errors. Bursting modulation was potent and its time course evolved, even in cells that were considered unresponsive based on the firing rate. During the later stages of training, this modulation in bursting happened earlier, gradually aligning temporally with the representation in event rate. The alignment of bursting and event rate modulation sharpened the firing rate response, and was strongly associated behavioral accuracy. Thus a fine-grained separation of spike timing patterns reveals two signals that accompany stimulus representations: an error signal that can be essential to guide learning and a sharpening signal that could implement attention mechanisms.

2024-03-27

bioRxiv (preprint)