Blake Richards

ali.sahebpasand@mila.quebec

Ali Saheb Pasand

Doctorat - McGill University

Superviseur⋅e principal⋅e :

Pouya Bashivan

Alissia Di Maria

Stagiaire de recherche - McGill University

alissia.dimaria@mila.quebec

Ann Huang

Collaborateur·rice alumni

zixiang.huang@mila.quebec

Arna Ghosh

Doctorat - McGill University

Chen Chen

Postdoctorat - Université de Montréal

Superviseur⋅e principal⋅e :

Yoshua Bengio

chen.sun@mila.quebec

Colin Bredenberg

Postdoctorat - Université de Montréal

Superviseur⋅e principal⋅e :

colin.bredenberg@mila.quebec

Dane Malenfant

Maîtrise recherche - McGill University

dane.malenfant@mila.quebec

daniel.levenstein@mila.quebec

Daniel Levenstein

Postdoctorat - McGill University

divyansha.lachi@mila.quebec

Divyansha Lachi

Collaborateur·rice de recherche - Georgia Tech

erica.cianfarano@mila.quebec

Dongyan Lin

Doctorat - McGill University

lindongy@mila.quebec

Erica Cianfarano

Doctorat - McGill University

Ethan Caballero

Doctorat - McGill University

Co-superviseur⋅e :

Irina Rish

ethan.caballero@mila.quebec

etienne.barou-laforie@mila.quebec

Etienne Barou-Laforie

Stagiaire de recherche - McGill University

Jonathan Cornford

Postdoctorat - McGill University

cornforj@mila.quebec

Josh Tindall

Maîtrise recherche - McGill University

joshua.tindall@mila.quebec

Mandana Samiei

Doctorat - McGill University

Superviseur⋅e principal⋅e :

Doctorat - McGill University

Mohammad Yaghoubi

Doctorat - McGill University

yaghoubm@mila.quebec

Quinn Lee

Postdoctorat - McGill University

j.quinn.lee@mila.quebec

Ray Chua

Doctorat - McGill University

Superviseur⋅e principal⋅e :

Doina Precup

chuaraym@mila.quebec

Roman Pogodin

Postdoctorat - McGill University

Co-superviseur⋅e :

Roman.Pogodin@mila.Quebec

Doctorat - McGill University

roy.eyono@mila.quebec

santiago.jaramillo@mila.quebec

Santiago Jaramillo

Visiteur de recherche indépendant - University of Oregon

Sonia Joseph

Doctorat - McGill University

sonia.joseph@mila.quebec

vemund.schoyen@mila.quebec

Surya Penmetsa

Collaborateur·rice alumni

penmetss@mila.quebec

Vemund Schoyen

Stagiaire de recherche - University of Oslo

Krystal Pan

Maîtrise recherche - McGill University

xuejing.pan@mila.quebec

Billets de blogue

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

Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL

Chen Sun

Wannan Yang

Thomas Jiralerspong

Dane Malenfant

Benjamin Alsbury-Nealy

Yoshua Bengio

In real life, success is often contingent upon multiple critical steps that are distant in time from each other and from the final reward. T… (voir plus)hese critical steps are challenging to identify with traditional reinforcement learning (RL) methods that rely on the Bellman equation for credit assignment. Here, we present a new RL algorithm that uses offline contrastive learning to hone in on these critical steps. This algorithm, which we call Contrastive Retrospection (ConSpec), can be added to any existing RL algorithm. ConSpec learns a set of prototypes for the critical steps in a task by a novel contrastive loss and delivers an intrinsic reward when the current state matches one of the prototypes. The prototypes in ConSpec provide two key benefits for credit assignment: (i) They enable rapid identification of all the critical steps. (ii) They do so in a readily interpretable manner, enabling out-of-distribution generalization when sensory features are altered. Distinct from other contemporary RL approaches to credit assignment, ConSpec takes advantage of the fact that it is easier to retrospectively identify the small set of steps that success is contingent upon (and ignoring other states) than it is to prospectively predict reward at every taken step. ConSpec greatly improves learning in a diverse set of RL tasks. The code is available at the link: https://github.com/sunchipsster1/ConSpec

Learning better with Dale’s Law: A Spectral Perspective

Pingsheng Li

Jonathan Cornford

Arna Ghosh

A Unified, Scalable Framework for Neural Population Decoding

Mehdi Azabou

Vinam Arora

Venkataramana Ganesh

Ximeng Mao

Santosh B Nachimuthu

Michael Jacob Mendelson

Matt Perich

Eva L Dyer

Our ability to use deep learning approaches to decipher neural activity would likely benefit from greater scale, in terms of both the model … (voir plus)size and the datasets. However, the integration of many neural recordings into one unified model is challenging, as each recording contains the activity of different neurons from different individual animals. In this paper, we introduce a training framework and architecture designed to model the population dynamics of neural activity across diverse, large-scale neural recordings. Our method first tokenizes individual spikes within the dataset to build an efficient representation of neural events that captures the fine temporal structure of neural activity. We then employ cross-attention and a PerceiverIO backbone to further construct a latent tokenization of neural population activities. Utilizing this architecture and training framework, we construct a large-scale multi-session model trained on large datasets from seven nonhuman primates, spanning over 158 different sessions of recording from over 27,373 neural units and over 100 hours of recordings. In a number of different tasks, we demonstrate that our pretrained model can be rapidly adapted to new, unseen sessions with unspecified neuron correspondence, enabling few-shot performance with minimal labels. This work presents a powerful new approach for building deep learning tools to analyze neural data and stakes out a clear path to training at scale for neural decoding models.

The neuroconnectionist research programme

Adrien C. Doerig

R. Sommers

Katja Seeliger

J. Ismael

Grace W. Lindsay

Konrad Paul Kording

Talia Konkle

M. Gerven

Nikolaus Kriegeskorte

Tim Kietzmann

2023-05-30

Nature Reviews Neuroscience (publié)

arxiv.org

Responses of pyramidal cell somata and apical dendrites in mouse visual cortex over multiple days

Colleen J Gillon

Jérôme A. Lecoq

Jason E. Pina

Ruweida Ahmed

Yazan N. Billeh

Shiella Caldejon

Peter Groblewski

Timothy M. Henley

India Kato

Eric Lee

Jennifer Luviano

Kyla Mace

Chelsea Nayan

Thuyanh V. Nguyen

Kat North

Jed Perkins

Sam Seid

Matthew T. Valley

Ali Williford

Yoshua Bengio … (voir 3 de plus)

Timothy P. Lillicrap

Joel Zylberberg

2023-05-17

Scientific Data (publié)

The study of plasticity has always been about gradients

Konrad Paul Kording

2023-05-01

The Journal of Physiology (publié)

Catalyzing next-generation Artificial Intelligence through NeuroAI

Anthony Zador

Sean Escola

Bence Ölveczky

Yoshua Bengio

Kwabena Boahen

Matthew Botvinick

Dmitri Chklovskii

Anne Churchland

Claudia Clopath

James DiCarlo

Surya

Surya Ganguli

Jeff Hawkins

Konrad Paul Kording

Alexei Koulakov

Yann LeCun

Timothy P. Lillicrap

Adam

Adam Marblestone … (voir 9 de plus)

Bruno Olshausen

Alexandre Pouget

Cristina Savin

Terrence Sejnowski

Eero Simoncelli

Sara Solla

David Sussillo

Andreas S. Tolias

Doris Tsao

2023-03-22

Nature Communications (publié)

Transfer Entropy Bottleneck: Learning Sequence to Sequence Information Transfer

Damjan Kalajdzievski

Ximeng Mao

Pascal Fortier-Poisson

When presented with a data stream of two statistically dependent variables, predicting the future of one of the variables (the target stream… (voir plus)) can benefit from information about both its history and the history of the other variable (the source stream). For example, fluctuations in temperature at a weather station can be predicted using both temperatures and barometric readings. However, a challenge when modelling such data is that it is easy for a neural network to rely on the greatest joint correlations within the target stream, which may ignore a crucial but small information transfer from the source to the target stream. As well, there are often situations where the target stream may have previously been modelled independently and it would be useful to use that model to inform a new joint model. Here, we develop an information bottleneck approach for conditional learning on two dependent streams of data. Our method, which we call Transfer Entropy Bottleneck (TEB), allows one to learn a model that bottlenecks the directed information transferred from the source variable to the target variable, while quantifying this information transfer within the model. As such, TEB provides a useful new information bottleneck approach for modelling two statistically dependent streams of data in order to make predictions about one of them.

2023-03-08

TMLR (accepté)

How gradient estimator variance and bias impact learning in neural networks

Arna Ghosh

Yuhan Helena Liu

Konrad Paul Kording

There is growing interest in understanding how real brains may approximate gradients and how gradients can be used to train neuromorphic chi… (voir plus)ps. However, neither real brains nor neuromorphic chips can perfectly follow the loss gradient, so parameter updates would necessarily use gradient estimators that have some variance and/or bias. Therefore, there is a need to understand better how variance and bias in gradient estimators impact learning dependent on network and task properties. Here, we show that variance and bias can impair learning on the training data, but some degree of variance and bias in a gradient estimator can be beneficial for generalization. We find that the ideal amount of variance and bias in a gradient estimator are dependent on several properties of the network and task: the size and activity sparsity of the network, the norm of the gradient, and the curvature of the loss landscape. As such, whether considering biologically-plausible learning algorithms or algorithms for training neuromorphic chips, researchers can analyze these properties to determine whether their approximation to gradient descent will be effective for learning given their network and task properties.

2023-02-01

ICLR.cc/2023/Conference (poster)