Portrait de Yoshua Bengio

Yoshua Bengio

Membre académique principal

Chaire en IA Canada-CIFAR

Professeur titulaire, Université de Montréal

Sujets de recherche

Apprentissage automatique médical

Apprentissage de représentations

Apprentissage par renforcement

Apprentissage profond

Causalité

Modèles génératifs

Modèles probabilistes

Modélisation moléculaire

Neurosciences computationnelles

Raisonnement

Réseaux de neurones en graphes

Réseaux de neurones récurrents

Théorie de l'apprentissage automatique

Traitement du langage naturel

Biographie

*Pour toute demande média, veuillez écrire à medias@mila.quebec.

Pour plus d’information, contactez Cassidy MacNeil, adjointe principale et responsable des opérations cassidy.macneil@mila.quebec.

Reconnu comme une sommité mondiale en intelligence artificielle, Yoshua Bengio s’est surtout distingué par son rôle de pionnier en apprentissage profond, ce qui lui a valu le prix A. M. Turing 2018, le « prix Nobel de l’informatique », avec Geoffrey Hinton et Yann LeCun. Il est professeur titulaire à l’Université de Montréal, fondateur et conseiller scientifique de Mila – Institut québécois d’intelligence artificielle, et codirige en tant que senior fellow le programme Apprentissage automatique, apprentissage biologique de l'Institut canadien de recherches avancées (CIFAR). Il occupe également la fonction de conseiller spécial et directeur scientifique fondateur d’IVADO.

En 2018, il a été l’informaticien qui a recueilli le plus grand nombre de nouvelles citations au monde. En 2019, il s’est vu décerner le prestigieux prix Killam. Depuis 2022, il détient le plus grand facteur d’impact (h-index) en informatique à l’échelle mondiale. Il est fellow de la Royal Society de Londres et de la Société royale du Canada, et officier de l’Ordre du Canada.

Soucieux des répercussions sociales de l’IA et de l’objectif que l’IA bénéficie à tous, il a contribué activement à la Déclaration de Montréal pour un développement responsable de l’intelligence artificielle.

Étudiants actuels

Jamal Abou Haibeh

Collaborateur·rice alumni - McGill

jamal.abouhaibeh@mila.quebec

Collaborateur·rice de recherche - Cambridge University

Superviseur⋅e principal⋅e :

berkes.anais@mila.quebec

Doctorat - UdeM

assouelr@mila.quebec

Doctorat - UdeM

xiaoyin.chen@mila.quebec

Collaborateur·rice de recherche - KAIST

sanghyeok.choi@mila.quebec

Aniket Didolkar

Doctorat - UdeM

aniket.didolkar@mila.quebec

Doctorat - UdeM

Co-superviseur⋅e :

Guillaume Lajoie

eric.elmoznino@mila.quebec

Doctorat - UdeM

lena-nehale.ezzine@mila.quebec

Jean-Pierre Falet

Doctorat - UdeM

jean-pierre.falet@mila.quebec

Doctorat

pietro.greiner@mila.quebec

Doctorat - UdeM

mohsin.hasan@mila.quebec

Doctorat - UdeM

moksh.jain@mila.quebec

Thomas Jiralerspong

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Guillaume Lajoie

thomas.jiralerspong@mila.quebec

Younesse Kaddar

Collaborateur·rice alumni - UdeM

younesse.kaddar@mila.quebec

Postdoctorat - UdeM

Superviseur⋅e principal⋅e :

Alex Hernández-García

hyeonah.kim@mila.quebec

Collaborateur·rice de recherche - UdeM

minsu.kim@mila.quebec

Collaborateur·rice de recherche - KOREA ADVANCED INSTITUTE OF SCIENCE AND TECHNOLOGY

jeongjae.lee@mila.quebec

Collaborateur·rice de recherche - s.o.

liusong299@gmail.com

Collaborateur·rice de recherche

liucheng@mila.quebec

Cristian Dragos Manta

Doctorat - UdeM

Co-superviseur⋅e :

cristian-dragos.manta@mila.quebec

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Guillaume Lajoie

mittalsa@mila.quebec

Visiteur de recherche indépendant - UdeM

nguyenph@mila.quebec

Collaborateur·rice de recherche - Ying Wu Coll of Computing

ali.parviz@mila.quebec

Collaborateur·rice de recherche - University of Waterloo

Superviseur⋅e principal⋅e :

elena.podina@mila.quebec

Jarrid Rector-Brooks

Doctorat - UdeM

jarrid.rector-brooks@mila.quebec

Postdoctorat - UdeM

danyal.rehman@mila.quebec

Postdoctorat - UdeM

oliver.richardson@mila.quebec

Camille Rochefort-Boulanger

Doctorat - UdeM

Superviseur⋅e principal⋅e :

rochefoc@mila.quebec

Postdoctorat - UdeM

Co-superviseur⋅e :

Alex Hernández-García

divya.sharma@mila.quebec

Mélisande Astrid Crystal Teng

Collaborateur·rice alumni - UdeM

Co-superviseur⋅e :

Hugo Larochelle

tengmeli@mila.quebec

Collaborateur·rice alumni - UdeM

alexander.tong@mila.quebec

Collaborateur·rice de recherche - University of Cambridge

oszkar.urban@mila.quebec

Collaborateur·rice alumni - UdeM

Co-superviseur⋅e :

donna.vakalis@mila.quebec

Siddarth Venkatraman

Doctorat - UdeM

Superviseur⋅e principal⋅e :

siddarth.venkatraman@mila.quebec

Collaborateur·rice de recherche

joseph.viviano2@mila.quebec

Esmeralda Whitammer

Collaborateur·rice de recherche - UdeM

esmeralda.whitammer@mila.quebec

Collaborateur·rice alumni

omar.younis@mila.quebec

Collaborateur·rice de recherche - UdeM

taeyoung.yun@mila.quebec

Doctorat - UdeM

tianyu.zhang@mila.quebec

Doctorat - McGill

Superviseur⋅e principal⋅e :

Mathieu Blanchette

xi.zhang@mila.quebec

Collaborateur·rice alumni - McGill

Superviseur⋅e principal⋅e :

zhaoming@mila.quebec

Billets de blogue

Generic thumbnail for Mila Blog articles.

22 février 2024

Skipper : combiner l’abstraction spatiale et temporelle afin d’améliorer la généralisation

par

Mingde Harry Zhao

Safa Alver

Harm van Seijen

Romain Laroche

Scaling in the service of reasoning & model-based ML

4 avril 2023

Mise à l’échelle au service du raisonnement et de l’apprentissage automatique basé sur un modèle

par

A collaboration between Mila and Relation Therapeutics to discover novel synergistic combinations of drugs in vitro

23 mars 2022

Une collaboration entre Mila et Relation Therapeutics pour découvrir in vitro de nouvelles associations médicamenteuses synergiques

par

Jake P. Taylor-King

Generative Flow Networks

15 mars 2022

Les réseaux de flot génératifs

par

Publications

Quantized Guided Pruning for Efficient Hardware Implementations of Deep Neural Networks

Ghouthi Boukli hacene

Matthieu Arzel

Nicolas Farrugia

Deep Neural Networks (DNNs) in general and Convolutional Neural Networks (CNNs) in particular are state-of-the-art in numerous computer visi… (voir plus)on tasks such as object classification and detection. However, the large amount of parameters they contain leads to a high computational complexity and strongly limits their usability in budget-constrained devices such as embedded devices. In this paper, we propose a combination of a pruning technique and a quantization scheme that effectively reduce the complexity and memory usage of convolutional layers of CNNs, by replacing the complex convolutional operation by a low-cost multiplexer. We perform experiments on CIFAR10, CIFAR100 and SVHN datasets and show that the proposed method achieves almost state-of-the-art accuracy, while drastically reducing the computational and memory footprints compared to the baselines. We also propose an efficient hardware architecture, implemented on Field Programmable Gate Arrays (FPGAs), to accelerate inference, which works as a pipeline and accommodates multiple layers working at the same time to speed up the inference process. In contrast with most proposed approaches which have used external memory or software defined memory controllers, our work is based on algorithmic optimization and full-hardware design, enabling a direct, on-chip memory implementation of a DNN while keeping close to state of the art accuracy.

2020-06-15

IEEE New Circuits and Systems Conference (publié)

Learning Causal Models Online

Martha White

2020-06-11

ArXiv (prépublication)

A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM

Iulian V. Serban

Varun Gupta

Ekaterina Kochmar

Dung D. Vu

Robert Belfer

Aaron Courville

Laurent Charlin

2020-06-09

Artificial Intelligence in Education (publié)

BigBrain 3D atlas of cortical layers: Cortical and laminar thickness gradients diverge in sensory and motor cortices

Konrad Wagstyl

Stéphanie Larocque

Guillem Cucurull

Claude Lepage

Joseph Paul Cohen

Sebastian Bludau

Nicola Palomero-Gallagher

Lindsay B. Lewis

Thomas Funck

Hannah Spitzer

Timo Dickscheid

Paul C. Fletcher

Adriana Romero

Karl Zilles

Katrin Amunts

Alan C. Evans

Histological atlases of the cerebral cortex, such as those made famous by Brodmann and von Economo, are invaluable for understanding human b… (voir plus)rain microstructure and its relationship with functional organization in the brain. However, these existing atlases are limited to small numbers of manually annotated samples from a single cerebral hemisphere, measured from 2D histological sections. We present the first whole-brain quantitative 3D laminar atlas of the human cerebral cortex. This atlas was derived from a 3D histological model of the human brain at 20 micron isotropic resolution (BigBrain), using a convolutional neural network to segment, automatically, the cortical layers in both hemispheres. Our approach overcomes many of the historical challenges with measurement of histological thickness in 2D and the resultant laminar atlas provides an unprecedented level of precision and detail. We utilized this BigBrain cortical atlas to test whether previously reported thickness gradients, as measured by MRI in sensory and motor processing cortices, were present in a histological atlas of cortical thickness, and which cortical layers were contributing to these gradients. Cortical thickness increased across sensory processing hierarchies, primarily driven by layers III, V and VI. In contrast, fronto-motor cortices showed the opposite pattern, with decreases in total and pyramidal layer thickness. These findings illustrate how this laminar atlas will provide a link between single-neuron morphology, mesoscale cortical layering, macroscopic cortical thickness and, ultimately, functional neuroanatomy.

2020-06-04

Public Library of Science (publié)

On the interplay between noise and curvature and its effect on optimization and generalization

Valentin Thomas

Fabian Pedregosa

Bart Van Merriënboer

Pierre-Antoine Mangazol

Nicolas Le Roux

The speed at which one can minimize an expected loss using stochastic methods depends on two properties: the curvature of the loss and the v… (voir plus)ariance of the gradients. While most previous works focus on one or the other of these properties, we explore how their interaction affects optimization speed. Further, as the ultimate goal is good generalization performance, we clarify how both curvature and noise are relevant to properly estimate the generalization gap. Realizing that the limitations of some existing works stems from a confusion between these matrices, we also clarify the distinction between the Fisher matrix, the Hessian, and the covariance matrix of the gradients.

2020-06-02

Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (publié)

proceedings.mlr.press

The need for privacy with public digital contact tracing during the COVID-19 pandemic

Richard Janda

Yun William Yu

Daphne Ippolito

Max Jarvie

Dan Pilat

Brooke Struck

Sekoul Krastev

Abhinav Sharma

2020-06-01

The Lancet Digital Health (publié)

Training End-to-End Analog Neural Networks with Equilibrium Propagation

Jack D. Kendall

Ross D. Pantone

Kalpana Manickavasagam

Benjamin Scellier

We introduce a principled method to train end-to-end analog neural networks by stochastic gradient descent. In these analog neural networks,… (voir plus) the weights to be adjusted are implemented by the conductances of programmable resistive devices such as memristors [Chua, 1971], and the nonlinear transfer functions (or `activation functions') are implemented by nonlinear components such as diodes. We show mathematically that a class of analog neural networks (called nonlinear resistive networks) are energy-based models: they possess an energy function as a consequence of Kirchhoff's laws governing electrical circuits. This property enables us to train them using the Equilibrium Propagation framework [Scellier and Bengio, 2017]. Our update rule for each conductance, which is local and relies solely on the voltage drop across the corresponding resistor, is shown to compute the gradient of the loss function. Our numerical simulations, which use the SPICE-based Spectre simulation framework to simulate the dynamics of electrical circuits, demonstrate training on the MNIST classification task, performing comparably or better than equivalent-size software-based neural networks. Our work can guide the development of a new generation of ultra-fast, compact and low-power neural networks supporting on-chip learning.

2020-06-01

ArXiv (prépublication)

Multi-Image Super-Resolution for Remote Sensing using Deep Recurrent Networks

Md Rifat Arefin

Vincent Michalski

Pierre-Luc St-Charles

Alfredo Kalaitzis

Sookyung Kim

Samira E. Kahou

High-resolution satellite imagery is critical for various earth observation applications related to environment monitoring, geoscience, fore… (voir plus)casting, and land use analysis. However, the acquisition cost of such high-quality imagery due to the scarcity of providers and needs for high-frequency revisits restricts its accessibility in many fields. In this work, we present a data-driven, multi-image super resolution approach to alleviate these problems. Our approach is based on an end-to-end deep neural network that consists of an encoder, a fusion module, and a decoder. The encoder extracts co-registered highly efficient feature representations from low-resolution images of a scene. A Gated Re-current Unit (GRU)-based module acts as the fusion module, aggregating features into a combined representation. Finally, a decoder reconstructs the super-resolved image. The proposed model is evaluated on the PROBA-V dataset released in a recent competition held by the European Space Agency. Our results show that it performs among the top contenders and offers a new practical solution for real-world applications.

2020-05-31

2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (publié)

Multi-Task Self-Supervised Learning for Robust Speech Recognition

Mirco Ravanelli

Santiago Pascual

Pawel Swietojanski

Joao Monteiro

Jan Trmal

Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To t… (voir plus)ake a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that combines a convolutional encoder followed by multiple neural networks, called workers, tasked to solve self-supervised problems (i.e., ones that do not require manual annotations as ground truth). PASE was shown to capture relevant speech information, including speaker voice-print and phonemes. This paper proposes PASE+, an improved version of PASE for robust speech recognition in noisy and reverberant environments. To this end, we employ an online speech distortion module, that contaminates the input signals with a variety of random disturbances. We then propose a revised encoder that better learns short- and long-term speech dynamics with an efficient combination of recurrent and convolutional networks. Finally, we refine the set of workers used in self-supervision to encourage better cooperation. Results on TIMIT, DIRHA and CHiME-5 show that PASE+ significantly outperforms both the previous version of PASE as well as common acoustic features. Interestingly, PASE+ learns transferable representations suitable for highly mismatched acoustic conditions.

2020-05-03

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (publié)

Continual Weight Updates and Convolutional Architectures for Equilibrium Propagation

Maxence Ernoult

Julie Grollier

Damien Querlioz

Benjamin Scellier

Equilibrium Propagation (EP) is a biologically inspired alternative algorithm to backpropagation (BP) for training neural networks. It appli… (voir plus)es to RNNs fed by a static input x that settle to a steady state, such as Hopfield networks. EP is similar to BP in that in the second phase of training, an error signal propagates backwards in the layers of the network, but contrary to BP, the learning rule of EP is spatially local. Nonetheless, EP suffers from two major limitations. On the one hand, due to its formulation in terms of real-time dynamics, EP entails long simulation times, which limits its applicability to practical tasks. On the other hand, the biological plausibility of EP is limited by the fact that its learning rule is not local in time: the synapse update is performed after the dynamics of the second phase have converged and requires information of the first phase that is no longer available physically. Our work addresses these two issues and aims at widening the spectrum of EP from standard machine learning models to more bio-realistic neural networks. First, we propose a discrete-time formulation of EP which enables to simplify equations, speed up training and extend EP to CNNs. Our CNN model achieves the best performance ever reported on MNIST with EP. Using the same discrete-time formulation, we introduce Continual Equilibrium Propagation (C-EP): the weights of the network are adjusted continually in the second phase of training using local information in space and time. We show that in the limit of slow changes of synaptic strengths and small nudging, C-EP is equivalent to BPTT (Theorem 1). We numerically demonstrate Theorem 1 and C-EP training on MNIST and generalize it to the bio-realistic situation of a neural network with asymmetric connections between neurons.

2020-04-28

ArXiv (prépublication)

Equilibrium Propagation with Continual Weight Updates

Maxence Ernoult

Julie Grollier

Damien Querlioz

Benjamin Scellier

Equilibrium Propagation (EP) is a learning algorithm that bridges Machine Learning and Neuroscience, by computing gradients closely matching… (voir plus) those of Backpropagation Through Time (BPTT), but with a learning rule local in space. Given an input

2020-04-28

arXiv (prépublication)

Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims

Miles Brundage

Shahar Avin

Jasmine Wang

Haydn Belfield

Gretchen Krueger

Gillian Hadfield

Heidy Khlaaf

Jingying Yang

Helen Toner

Ruth Fong

Pang Wei Koh

Sara Hooker

Jade Leung

Andrew Trask

Emma Bluemke

Jonathan Lebensold

Cullen O’Keefe

Mark Koren

Théo Ryffel … (voir 39 de plus)

JB Rubinovitz

Tamay Besiroglu

Federica Carugati

Jack Clark

Peter Eckersley

Sarah de Haas

Maritza Johnson

Ben Laurie

Alex Ingerman

Igor Krawczuk

Amanda Askell

Rosario Cammarota

Andrew Lohn

David Krueger

Charlotte Stix

Peter Henderson

Logan Graham

Carina Prunkl

Bianca Martin

Elizabeth Seger

Noa Zilberman

Seán Ó hÉigeartaigh

Frens Kroeger

Girish Sastry

Rebecca Kagan

Adrian Weller

Brian Tse

Elizabeth Barnes

Allan Dafoe

Paul Scharre

Ariel Herbert-Voss

Martijn Rasser

Carrick Flynn

Thomas Krendl Gilbert

Lisa Dyer

Saif Khan

Markus Anderljung

With the recent wave of progress in artificial intelligence (AI) has come a growing awareness of the large-scale impacts of AI systems, and … (voir plus)recognition that existing regulations and norms in industry and academia are insufficient to ensure responsible AI development. In order for AI developers to earn trust from system users, customers, civil society, governments, and other stakeholders that they are building AI responsibly, they will need to make verifiable claims to which they can be held accountable. Those outside of a given organization also need effective means of scrutinizing such claims. This report suggests various steps that different stakeholders can take to improve the verifiability of claims made about AI systems and their associated development processes, with a focus on providing evidence about the safety, security, fairness, and privacy protection of AI systems. We analyze ten mechanisms for this purpose--spanning institutions, software, and hardware--and make recommendations aimed at implementing, exploring, or improving those mechanisms.

2020-04-14

arXiv (prépublication)