Portrait de Yoshua Bengio

Yoshua Bengio

Membre académique principal
Chaire en IA Canada-CIFAR
Professeur titulaire, Université de Montréal, Département d'informatique et de recherche opérationnelle
Directeur scientifique, Équipe de direction
Observateur, Conseil d'administration, Mila

Biographie

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

Pour plus d’information, contactez Julie Mongeau, adjointe de direction à julie.mongeau@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 directeur 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 directeur scientifique 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

Maîtrise professionnelle - Université de Montréal
Co-superviseur⋅e :
Maîtrise professionnelle - Université de Montréal
Doctorat - Université de Montréal
Postdoctorat - Université de Montréal
Co-superviseur⋅e :
Postdoctorat - Université de Montréal
Doctorat - Université de Montréal
Collaborateur·rice de recherche - Université Paris-Saclay
Superviseur⋅e principal⋅e :
Maîtrise professionnelle - Université de Montréal
Visiteur de recherche indépendant - MIT
Doctorat - École Polytechnique Montréal Fédérale de Lausanne
Stagiaire de recherche - Université du Québec à Rimouski
Collaborateur·rice de recherche
Superviseur⋅e principal⋅e :
Doctorat - Université de Montréal
Superviseur⋅e principal⋅e :
Postdoctorat - Université de Montréal
Co-superviseur⋅e :
Maîtrise professionnelle - Université de Montréal
Doctorat - Université de Montréal
Co-superviseur⋅e :
Doctorat - Barcelona University
Doctorat - Université de Montréal
Superviseur⋅e principal⋅e :
Postdoctorat - Université de Montréal
Co-superviseur⋅e :
Maîtrise recherche - Université de Montréal
Doctorat - Université de Montréal
Stagiaire de recherche - Université de Montréal
Doctorat - Université de Montréal
Co-superviseur⋅e :
Stagiaire de recherche - UQAR
Collaborateur·rice alumni
Visiteur de recherche indépendant - Université de Montréal
Doctorat - Université de Montréal
Superviseur⋅e principal⋅e :
Stagiaire de recherche - McGill University
Visiteur de recherche indépendant - Université de Montréal
Doctorat - Université de Montréal
Co-superviseur⋅e :
Doctorat - Université de Montréal
Co-superviseur⋅e :
Maîtrise professionnelle - Université de Montréal
Stagiaire de recherche - Université de Montréal
Doctorat - Université de Montréal
Doctorat - Massachusetts Institute of Technology
Doctorat - Université de Montréal
Doctorat - Université de Montréal
Visiteur de recherche indépendant - Technical University Munich (TUM)
Visiteur de recherche indépendant - Hong Kong University of Science and Technology (HKUST)
DESS - Université de Montréal
Visiteur de recherche indépendant - UQAR
Postdoctorat - Université de Montréal
Doctorat - Université de Montréal
Stagiaire de recherche - Université de Montréal
Visiteur de recherche indépendant - Technical University of Munich
Stagiaire de recherche - Imperial College London
Doctorat - Université de Montréal
Co-superviseur⋅e :
Postdoctorat - Université de Montréal
Doctorat - McGill University
Superviseur⋅e principal⋅e :
Maîtrise professionnelle - Université de Montréal
Collaborateur·rice de recherche - Université de Montréal
Stagiaire de recherche - Université de Montréal
Stagiaire de recherche - Université de Montréal
Doctorat - Université de Montréal
Doctorat - Max-Planck-Institute for Intelligent Systems
Doctorat - McGill University
Superviseur⋅e principal⋅e :
Collaborateur·rice alumni - Université de Montréal
Maîtrise professionnelle - Université de Montréal
Doctorat - Université de Montréal
Visiteur de recherche indépendant - Université de Montréal
Collaborateur·rice alumni - Université de Montréal
Collaborateur·rice de recherche
Maîtrise professionnelle - Université de Montréal
Collaborateur·rice de recherche - Valence
Superviseur⋅e principal⋅e :
Doctorat - Université de Montréal
Doctorat - Université de Montréal
Superviseur⋅e principal⋅e :
Doctorat - Université de Montréal
Doctorat - Université de Montréal
Superviseur⋅e principal⋅e :
Stagiaire de recherche - Université de Montréal
Collaborateur·rice de recherche - Université de Montréal
Visiteur de recherche indépendant
Co-superviseur⋅e :
Postdoctorat - Université de Montréal
Stagiaire de recherche - McGill University
Maîtrise professionnelle - Université de Montréal
Collaborateur·rice de recherche
Superviseur⋅e principal⋅e :
Maîtrise recherche - Université de Montréal
Co-superviseur⋅e :
Doctorat - Université de Montréal
Maîtrise recherche - Université de Montréal
Doctorat - Université de Montréal
Collaborateur·rice de recherche - RWTH Aachen University (Rheinisch-Westfälische Technische Hochschule Aachen)
Superviseur⋅e principal⋅e :
Baccalauréat - Université de Montréal
Doctorat - Université de Montréal
Maîtrise professionnelle - Université de Montréal
Maîtrise professionnelle - Université de Montréal
Stagiaire de recherche - Université de Montréal
Doctorat - Université de Montréal
Superviseur⋅e principal⋅e :
Maîtrise professionnelle - Université de Montréal
Postdoctorat - Université de Montréal

Publications

Interpolated Adversarial Training: Achieving Robust Neural Networks without Sacrificing Accuracy
Alex Lamb
Vikas Verma
Juho Kannala
Adversarial robustness has become a central goal in deep learning, both in theory and practice. However, successful methods to improve adver… (voir plus)sarial robustness (such as adversarial training) greatly hurt generalization performance on the clean data. This could have a major impact on how adversarial robustness affects real world systems (i.e. many may opt to forego robustness if it can improve performance on the clean data). We propose Interpolated Adversarial Training, which employs recently proposed interpolation based training methods in the framework of adversarial training. On CIFAR-10, adversarial training increases clean test error from 5.8% to 16.7%, whereas with our Interpolated adversarial training we retain adversarial robustness while achieving a clean test error of only 6.5%. With our technique, the relative error increase for the robust model is reduced from 187.9% to just 12.1%.
Predicting Tactical Solutions to Operational Planning Problems under Imperfect Information
Eric P. Larsen
Sébastien Lachapelle
This paper offers a methodological contribution at the intersection of machine learning and operations research. Namely, we propose a method… (voir plus)ology to quickly predict expected tactical descriptions of operational solutions (TDOSs). The problem we address occurs in the context of two-stage stochastic programming, where the second stage is demanding computationally. We aim to predict at a high speed the expected TDOS associated with the second-stage problem, conditionally on the first-stage variables. This may be used in support of the solution to the overall two-stage problem by avoiding the online generation of multiple second-stage scenarios and solutions. We formulate the tactical prediction problem as a stochastic optimal prediction program, whose solution we approximate with supervised machine learning. The training data set consists of a large number of deterministic operational problems generated by controlled probabilistic sampling. The labels are computed based on solutions to these problems (solved independently and offline), employing appropriate aggregation and subselection methods to address uncertainty. Results on our motivating application on load planning for rail transportation show that deep learning models produce accurate predictions in very short computing time (milliseconds or less). The predictive accuracy is close to the lower bounds calculated based on sample average approximation of the stochastic prediction programs.
Information Fusion in Deep Convolutional Neural Networks for Biomedical Image Segmentation 1
Mohammad Havaei
Nicolas Guizard
Focused Hierarchical RNNs for Conditional Sequence Processing
Nan Rosemary Ke
Konrad Żołna
Zhouhan Lin
Adam Trischler
Recurrent Neural Networks (RNNs) with attention mechanisms have obtained state-of-the-art results for many sequence processing tasks. Most o… (voir plus)f these models use a simple form of encoder with attention that looks over the entire sequence and assigns a weight to each token independently. We present a mechanism for focusing RNN encoders for sequence modelling tasks which allows them to attend to key parts of the input as needed. We formulate this using a multi-layer conditional sequence encoder that reads in one token at a time and makes a discrete decision on whether the token is relevant to the context or question being asked. The discrete gating mechanism takes in the context embedding and the current hidden state as inputs and controls information flow into the layer above. We train it using policy gradient methods. We evaluate this method on several types of tasks with different attributes. First, we evaluate the method on synthetic tasks which allow us to evaluate the model for its generalization ability and probe the behavior of the gates in more controlled settings. We then evaluate this approach on large scale Question Answering tasks including the challenging MS MARCO and SearchQA tasks. Our models shows consistent improvements for both tasks over prior work and our baselines. It has also shown to generalize significantly better on synthetic tasks as compared to the baselines.
Commonsense mining as knowledge base completion? A study on the impact of novelty
Stanisław Jastrzębski
Seyedarian Hosseini
Michael Noukhovitch
Commonsense knowledge bases such as ConceptNet represent knowledge in the form of relational triples. Inspired by recent work by Li et al., … (voir plus)we analyse if knowledge base completion models can be used to mine commonsense knowledge from raw text. We propose novelty of predicted triples with respect to the training set as an important factor in interpreting results. We critically analyse the difficulty of mining novel commonsense knowledge, and show that a simple baseline method that outperforms the previous state of the art on predicting more novel triples.
Learning Anonymized Representations with Adversarial Neural Networks
Clément Feutry
P. Duhamel
Statistical methods protecting sensitive information or the identity of the data owner have become critical to ensure privacy of individuals… (voir plus) as well as of organizations. This paper investigates anonymization methods based on representation learning and deep neural networks, and motivated by novel information theoretical bounds. We introduce a novel training objective for simultaneously training a predictor over target variables of interest (the regular labels) while preventing an intermediate representation to be predictive of the private labels. The architecture is based on three sub-networks: one going from input to representation, one from representation to predicted regular labels, and one from representation to predicted private labels. The training procedure aims at learning representations that preserve the relevant part of the information (about regular labels) while dismissing information about the private labels which correspond to the identity of a person. We demonstrate the success of this approach for two distinct classification versus anonymization tasks (handwritten digits and sentiment analysis).
Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent Networks
Nan Rosemary Ke
Anirudh Goyal
Olexa Bilaniuk
Jonathan Binas
A major drawback of backpropagation through time (BPTT) is the difficulty of learning long-term dependencies, coming from having to propagat… (voir plus)e credit information backwards through every single step of the forward computation. This makes BPTT both computationally impractical and biologically implausible. For this reason, full backpropagation through time is rarely used on long sequences, and truncated backpropagation through time is used as a heuristic. However, this usually leads to biased estimates of the gradient in which longer term dependencies are ignored. Addressing this issue, we propose an alternative algorithm, Sparse Attentive Backtracking, which might also be related to principles used by brains to learn long-term dependencies. Sparse Attentive Backtracking learns an attention mechanism over the hidden states of the past and selectively backpropagates through paths with high attention weights. This allows the model to learn long term dependencies while only backtracking for a small number of time steps, not just from the recent past but also from attended relevant past states.
Diet Networks: Thin Parameters for Fat Genomics
pierre luc carrier
Akram Erraqabi
Tristan Sylvain
Alex Auvolat
Etienne Dejoie
Marc-André Legault
Marie-Pierre Dubé
Learning tasks such as those involving genomic data often poses a serious challenge: the number of input features can be orders of magnitude… (voir plus) larger than the number of training examples, making it difficult to avoid overfitting, even when using the known regularization techniques. We focus here on tasks in which the input is a description of the genetic variation specific to a patient, the single nucleotide polymorphisms (SNPs), yielding millions of ternary inputs. Improving the ability of deep learning to handle such datasets could have an important impact in medical research, more specifically in precision medicine, where high-dimensional data regarding a particular patient is used to make predictions of interest. Even though the amount of data for such tasks is increasing, this mismatch between the number of examples and the number of inputs remains a concern. Naive implementations of classifier neural networks involve a huge number of free parameters in their first layer (number of input features times number of hidden units): each input feature is associated with as many parameters as there are hidden units. We propose a novel neural network parametrization which considerably reduces the number of free parameters. It is based on the idea that we can first learn or provide a distributed representation for each input feature (e.g. for each position in the genome where variations are observed in data), and then learn (with another neural network called the parameter prediction network) how to map a feature's distributed representation (based on the feature's identity not its value) to the vector of parameters specific to that feature in the classifier neural network (the weights which link the value of the feature to each of the hidden units). This approach views the problem of producing the parameters associated with each feature as a multi-task learning problem. We show experimentally on a population stratification task of interest to medical studies that the proposed approach can significantly reduce both the number of parameters and the error rate of the classifier.
Diet Networks: Thin Parameters for Fat Genomics
pierre luc carrier
Akram Erraqabi
Tristan Sylvain
Alex Auvolat
Etienne Dejoie
Marc-André Legault
Marie-Pierre Dubé
Learning tasks such as those involving genomic data often poses a serious challenge: the number of input features can be orders of magnitude… (voir plus) larger than the number of training examples, making it difficult to avoid overfitting, even when using the known regularization techniques. We focus here on tasks in which the input is a description of the genetic variation specific to a patient, the single nucleotide polymorphisms (SNPs), yielding millions of ternary inputs. Improving the ability of deep learning to handle such datasets could have an important impact in medical research, more specifically in precision medicine, where high-dimensional data regarding a particular patient is used to make predictions of interest. Even though the amount of data for such tasks is increasing, this mismatch between the number of examples and the number of inputs remains a concern. Naive implementations of classifier neural networks involve a huge number of free parameters in their first layer (number of input features times number of hidden units): each input feature is associated with as many parameters as there are hidden units. We propose a novel neural network parametrization which considerably reduces the number of free parameters. It is based on the idea that we can first learn or provide a distributed representation for each input feature (e.g. for each position in the genome where variations are observed in data), and then learn (with another neural network called the parameter prediction network) how to map a feature's distributed representation (based on the feature's identity not its value) to the vector of parameters specific to that feature in the classifier neural network (the weights which link the value of the feature to each of the hidden units). This approach views the problem of producing the parameters associated with each feature as a multi-task learning problem. We show experimentally on a population stratification task of interest to medical studies that the proposed approach can significantly reduce both the number of parameters and the error rate of the classifier.
Diet Networks: Thin Parameters for Fat Genomic
pierre luc carrier
Akram Erraqabi
Tristan Sylvain
Alex Auvolat
Etienne Dejoie
Marc-andr'e Legault
M. Dubé
Learning tasks such as those involving genomic data often poses a serious challenge: the number of input features can be orders of magnitude… (voir plus) larger than the number of training examples, making it difficult to avoid overfitting, even when using the known regularization techniques. We focus here on tasks in which the input is a description of the genetic variation specific to a patient, the single nucleotide polymorphisms (SNPs), yielding millions of ternary inputs. Improving the ability of deep learning to handle such datasets could have an important impact in precision medicine, where high-dimensional data regarding a particular patient is used to make predictions of interest. Even though the amount of data for such tasks is increasing, this mismatch between the number of examples and the number of inputs remains a concern. Naive implementations of classifier neural networks involve a huge number of free parameters in their first layer: each input feature is associated with as many parameters as there are hidden units. We propose a novel neural network parametrization which considerably reduces the number of free parameters. It is based on the idea that we can first learn or provide a distributed representation for each input feature (e.g. for each position in the genome where variations are observed), and then learn (with another neural network called the parameter prediction network) how to map a feature's distributed representation to the vector of parameters specific to that feature in the classifier neural network (the weights which link the value of the feature to each of the hidden units). We show experimentally on a population stratification task of interest to medical studies that the proposed approach can significantly reduce both the number of parameters and the error rate of the classifier.
HeMIS: Hetero-Modal Image Segmentation
Mohammad Havaei
Nicolas Guizard
HeMIS: Hetero-Modal Image Segmentation
Mohammad Havaei
Nicolas Guizard