Yoshua Bengio

Biography

*For media requests, please write to medias@mila.quebec.

For more information please contact Marie-Josée Beauchamp, Administrative Assistant at marie-josee.beauchamp@mila.quebec.

Yoshua Bengio is recognized worldwide as a leading expert in AI. He is most known for his pioneering work in deep learning, which earned him the 2018 A.M. Turing Award, “the Nobel Prize of computing,” with Geoffrey Hinton and Yann LeCun.

Bengio is a full professor at Université de Montréal, and the founder and scientific advisor of Mila – Quebec Artificial Intelligence Institute. He is also a senior fellow at CIFAR and co-directs its Learning in Machines & Brains program, serves as special advisor and founding scientific director of IVADO, and holds a Canada CIFAR AI Chair.

In 2019, Bengio was awarded the prestigious Killam Prize and in 2022, he was the most cited computer scientist in the world by h-index. He is a Fellow of the Royal Society of London, Fellow of the Royal Society of Canada, Knight of the Legion of Honor of France and Officer of the Order of Canada. In 2023, he was appointed to the UN’s Scientific Advisory Board for Independent Advice on Breakthroughs in Science and Technology.

Concerned about the social impact of AI, Bengio helped draft the Montréal Declaration for the Responsible Development of Artificial Intelligence and continues to raise awareness about the importance of mitigating the potentially catastrophic risks associated with future AI systems.

Current Students

Jamal Abou Haibeh

Collaborating Alumni - McGill University

Mohammed Abukalam

Collaborating Alumni - Université de Montréal

agassoussisalwane2@gmail.com

Salwane Agassoussi

Université de Montréal

Berkes Anaïs

Collaborating researcher - Cambridge University

Principal supervisor :

Rim Assouel

PhD - Université de Montréal

Ayoub Atanane

Collaborating Alumni - Université du Québec à Rimouski

Stefan Bauer

Independent visiting researcher

Co-supervisor :

Guillaume Lajoie

Paul Bertin

PhD - Université de Montréal

Ghait Boukachab

Collaborating Alumni - UQAR

Shahana Chatterjee

Collaborating researcher - N/A

Principal supervisor :

David Rolnick

Xiaoyin Chen

PhD - Université de Montréal

Sanghyeok Choi

Collaborating researcher - KAIST

PhD - Université de Montréal

PhD - Université de Montréal

Collaborating Alumni - Université de Montréal

Eric Elmoznino

PhD - Université de Montréal

Co-supervisor :

PhD - Université de Montréal

Léna Ezzine

PhD - Université de Montréal

Jean-Pierre Falet

PhD - Université de Montréal

Co-supervisor :

Leo Feng

PhD - Université de Montréal

Research Intern - Université de Montréal

Ivan Grega

Research Intern - Université de Montréal

Pietro Greiner

PhD

Mohsin Hasan

PhD - Université de Montréal

mohsin.hasan@mila.quebec

Edward Hu

PhD - Université de Montréal

Moksh Jain

PhD - Université de Montréal

moksh.jain@mila.quebec

Master's Research - Université de Montréal

Co-supervisor :

Collaborating Alumni - Université de Montréal

Minsu Kim

Research Intern - Université de Montréal

Collaborating researcher - Université de Montréal

Michał Koziarski

Collaborating Alumni - Université de Montréal

Salem Lahlou

Collaborating Alumni - Université de Montréal

Tabitha Edith Lee

Postdoctorate - Université de Montréal

Principal supervisor :

Seanie Lee

Collaborating Alumni - Université de Montréal

Collaborating Alumni

Zhen Liu

Collaborating Alumni - Université de Montréal

Principal supervisor :

Liam Paull

Matt MacDermott

Collaborating Alumni - Imperial College London

PhD - Université de Montréal

Mohammed Mahfoud

Collaborating Alumni - Université de Montréal

Nikolay Malkin

Collaborating Alumni - Université de Montréal

Cristian Dragos Manta

PhD - Université de Montréal

Co-supervisor :

Dhanya Sridhar

Sören Mindermann

Collaborating researcher - Université de Montréal

Sarthak Mittal

PhD - Université de Montréal

Principal supervisor :

PhD - Université de Montréal

Principal supervisor :

Postdoctorate - Université de Montréal

Principal supervisor :

Independent visiting researcher - Université de Montréal

Padideh Nouri

PhD - Université de Montréal

Principal supervisor :

Ali Parviz

Collaborating researcher - Ying Wu Coll of Computing

Lena Podina

PhD - University of Waterloo

Principal supervisor :

David Rolnick

Nassim Rahaman

Collaborating Alumni - Max-Planck-Institute for Intelligent Systems

Jarrid Rector-Brooks

PhD - Université de Montréal

Danyal REHMAN

Postdoctorate - Université de Montréal

James Requeima

Independent visiting researcher - Université de Montréal

Oli RICHARDSON

Postdoctorate - Université de Montréal

Camille Rochefort-Boulanger

PhD - Université de Montréal

Principal supervisor :

Julie Hussin

Victor Schmidt

Collaborating Alumni - Université de Montréal

Postdoctorate - Université de Montréal

Master's Research - Université de Montréal

Marcin Sendera

Collaborating Alumni - Université de Montréal

Dounia Shaaban Kabakibo

Research Intern - Université de Montréal

Vedant Shah

Master's Research - Université de Montréal

Postdoctorate

Marco Stock

Independent visiting researcher - Technical University of Munich

marco.stock@tum.de

Mélisande Astrid Crystal Teng

PhD - Université de Montréal

Co-supervisor :

Collaborating researcher - RWTH Aachen University (Rheinisch-Westfälische Technische Hochschule Aachen)

Principal supervisor :

David Rolnick

alexander.tong@mila.quebec

Alex Tong

Postdoctorate - Université de Montréal

Postdoctorate - Université de Montréal

Co-supervisor :

PhD - Université de Montréal

Principal supervisor :

Collaborating researcher - Université de Montréal

Zichao Yan

Collaborating Alumni - Université de Montréal

Omar G. Younis

Collaborating researcher

Collaborating researcher - KAIST

Tianyu Zhang

PhD - Université de Montréal

PhD - McGill University

Principal supervisor :

PhD - Université de Montréal

Principal supervisor :

Aaron Courville

Skipper: Combining Spatial and Temporal Abstraction for Better Generalization

Harry Zhao

PhD - McGill University

Principal supervisor :

Blog Posts

Generic thumbnail for Mila Blog articles.

February 22, 2024

Mingde Harry Zhao

Safa Alver

Harm van Seijen

Romain Laroche

Doina Precup

Yoshua Bengio

Scaling in the Service of Reasoning & Model-Based ML

April 4, 2023

Yoshua Bengio

Edward J. Hu

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

March 23, 2022

Paul Bertin

Jake P. Taylor-King

Yoshua Bengio

March 15, 2022

Generative Flow Networks

Yoshua Bengio

Publications

Online continual learning with no task boundaries

Rahaf Aljundi

Min Lin

Baptiste Goujaud

Continual learning is the ability of an agent to learn online with a non-stationary and never-ending stream of data. A key component for suc… (see more)h never-ending learning process is to overcome the catastrophic forgetting of previously seen data, a problem that neural networks are well known to suffer from. The solutions developed so far often relax the problem of continual learning to the easier task-incremental setting, where the stream of data is divided into tasks with clear boundaries. In this paper, we break the limits and move to the more challenging online setting where we assume no information of tasks in the data stream. We start from the idea that each learning step should not increase the losses of the previously learned examples through constraining the optimization process. This means that the number of constraints grows linearly with the number of examples, which is a serious limitation. We develop a solution to select a ﬁxed number of constraints that we use to approximate the feasible region deﬁned by the original constraints. We compare our approach against the methods that rely on task boundaries to select a ﬁxed set of examples, and show comparable or even better results, especially when the boundaries are blurry or when the data distributions are imbalanced.

2019-03-20

arXiv.org (preprint)

dblp.uni-trier.de

Automated segmentation of cortical layers in BigBrain reveals divergent cortical and laminar thickness gradients in sensory and motor cortices.

Konrad Wagstyl

Stéphanie Larocque

Guillem Cucurull

Claude Lepage

Joseph Paul Cohen

Sebastian Bludau

Nicola Palomero-Gallagher

L. Lewis

Thomas Funck

Hannah Spitzer

Timo Dicksheid

Paul C Fletcher

Adriana Romero Soriano

Karl Zilles

Katrin Amunts

Alan C. Evans

Abstract Large-scale in vivo neuroimaging datasets offer new possibilities for reliable, well-powered measures of interregional structural d… (see more)ifferences and biomarkers of pathological changes in a wide variety of neurological and psychiatric diseases. However, so far studies have been structurally and functionally imprecise, being unable to relate pathological changes to specific cortical layers or neurobiological processes. We developed artificial neural networks to segment cortical and laminar surfaces in the BigBrain, a 3D histological model of the human brain. We sought 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. Identifying common gradients of cortical organisation enables us to meaningfully relate microstructural, macrostructural and functional cortical parameters. Analysis of thickness gradients across sensory cortices, using our fully segmented six-layered model, was consistent with MRI findings, showing increasing thickness moving up the processing hierarchy. In contrast, fronto-motor cortices showed the opposite pattern with changes in thickness of layers III, V and VI being the primary drivers of these gradients. As well as identifying key differences between sensory and motor gradients, our findings show how the use of this laminar atlas offers insights that will be key to linking single-neuron morphological changes, mesoscale cortical layers and macroscale cortical thickness.

2019-03-17

bioRxiv (preprint)

doi.org

Interpolation Consistency Training for Semi-Supervised Learning

Vikas Verma

Alex Lamb

Juho Kannala

David Lopez-Paz

2019-03-09

ArXiv (preprint)

doi.org

Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future

Nan Rosemary Ke

Amanpreet Singh

Ahmed Touati

Anirudh Goyal

Devi Parikh

Dhruv Batra

In model-based reinforcement learning, the agent interleaves between model learning and planning. These two components are inextricably inte… (see more)rtwined. If the model is not able to provide sensible long-term prediction, the executed planner would exploit model flaws, which can yield catastrophic failures. This paper focuses on building a model that reasons about the long-term future and demonstrates how to use this for efficient planning and exploration. To this end, we build a latent-variable autoregressive model by leveraging recent ideas in variational inference. We argue that forcing latent variables to carry future information through an auxiliary task substantially improves long-term predictions. Moreover, by planning in the latent space, the planner's solution is ensured to be within regions where the model is valid. An exploration strategy can be devised by searching for unlikely trajectories under the model. Our method achieves higher reward faster compared to baselines on a variety of tasks and environments in both the imitation learning and model-based reinforcement learning settings.

2019-03-05

ArXiv (preprint)

Equivalence of Equilibrium Propagation and Recurrent Backpropagation

Benjamin Scellier

Recurrent backpropagation and equilibrium propagation are supervised learning algorithms for fixed-point recurrent neural networks, which di… (see more)ffer in their second phase. In the first phase, both algorithms converge to a fixed point that corresponds to the configuration where the prediction is made. In the second phase, equilibrium propagation relaxes to another nearby fixed point corresponding to smaller prediction error, whereas recurrent backpropagation uses a side network to compute error derivatives iteratively. In this work, we establish a close connection between these two algorithms. We show that at every moment in the second phase, the temporal derivatives of the neural activities in equilibrium propagation are equal to the error derivatives computed iteratively by recurrent backpropagation in the side network. This work shows that it is not required to have a side network for the computation of error derivatives and supports the hypothesis that in biological neural networks, temporal derivatives of neural activities may code for error signals.

2019-02-01

Neural Computation (published)

doi.org

Maximum Entropy Generators for Energy-Based Models

Rithesh Kumar

Anirudh Goyal

Aaron Courville

Maximum likelihood estimation of energy-based models is a challenging problem due to the intractability of the log-likelihood gradient. In t… (see more)his work, we propose learning both the energy function and an amortized approximate sampling mechanism using a neural generator network, which provides an efficient approximation of the log-likelihood gradient. The resulting objective requires maximizing entropy of the generated samples, which we perform using recently proposed nonparametric mutual information estimators. Finally, to stabilize the resulting adversarial game, we use a zero-centered gradient penalty derived as a necessary condition from the score matching literature. The proposed technique can generate sharp images with Inception and FID scores competitive with recent GAN techniques, does not suffer from mode collapse, and is competitive with state-of-the-art anomaly detection techniques.

2019-01-24

ArXiv (preprint)

The Benefits of Over-parameterization at Initialization in Deep ReLU Networks

Devansh Arpit

It has been noted in existing literature that over-parameterization in ReLU networks generally improves performance. While there could be se… (see more)veral factors involved behind this, we prove some desirable theoretical properties at initialization which may be enjoyed by ReLU networks. Specifically, it is known that He initialization in deep ReLU networks asymptotically preserves variance of activations in the forward pass and variance of gradients in the backward pass for infinitely wide networks, thus preserving the flow of information in both directions. Our paper goes beyond these results and shows novel properties that hold under He initialization: i) the norm of hidden activation of each layer is equal to the norm of the input, and, ii) the norm of weight gradient of each layer is equal to the product of norm of the input vector and the error at output layer. These results are derived using the PAC analysis framework, and hold true for finitely sized datasets such that the width of the ReLU network only needs to be larger than a certain finite lower bound. As we show, this lower bound depends on the depth of the network and the number of samples, and by the virtue of being a lower bound, over-parameterized ReLU networks are endowed with these desirable properties. For the aforementioned hidden activation norm property under He initialization, we further extend our theory and show that this property holds for a finite width network even when the number of data samples is infinite. Thus we overcome several limitations of existing papers, and show new properties of deep ReLU networks at initialization.

2019-01-11

ArXiv (preprint)

Adversarial Domain Adaptation for Stable Brain-Machine Interfaces

Ali Farshchian

Juan A. Gallego

Joseph Paul Cohen

Lee Miller

Sara Solla

Brain-Machine Interfaces (BMIs) have recently emerged as a clinically viable option to restore voluntary movements after paralysis. These de… (see more)vices are based on the ability to extract information about movement intent from neural signals recorded using multi-electrode arrays chronically implanted in the motor cortices of the brain. However, the inherent loss and turnover of recorded neurons requires repeated recalibrations of the interface, which can potentially alter the day-to-day user experience. The resulting need for continued user adaptation interferes with the natural, subconscious use of the BMI. Here, we introduce a new computational approach that decodes movement intent from a low-dimensional latent representation of the neural data. We implement various domain adaptation methods to stabilize the interface over significantly long times. This includes Canonical Correlation Analysis used to align the latent variables across days; this method requires prior point-to-point correspondence of the time series across domains. Alternatively, we match the empirical probability distributions of the latent variables across days through the minimization of their Kullback-Leibler divergence. These two methods provide a significant and comparable improvement in the performance of the interface. However, implementation of an Adversarial Domain Adaptation Network trained to match the empirical probability distribution of the residuals of the reconstructed neural signals outperforms the two methods based on latent variables, while requiring remarkably few data points to solve the domain adaptation problem.

2019-01-01

ICLR.cc/2019/Conference (poster)

On Adversarial Mixup Resynthesis

Christopher Beckham

Sina Honari

Alex Lamb

Vikas Verma

Farnoosh Ghadiri

(Rex) Devon Hjelm

Chris Pal

In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We explore mo… (see more)dels that are capable of combining the attributes of multiple inputs such that a resynthesised output is trained to fool an adversarial discriminator for real versus synthesised data. Furthermore, we explore the use of such an architecture in the context of semi-supervised learning, where we learn a mixing function whose objective is to produce interpolations of hidden states, or masked combinations of latent representations that are consistent with a conditioned class label. We show quantitative and qualitative evidence that such a formulation is an interesting avenue of research.

Artificial Intelligence Cytometer in Blood

Geoffrey Hinton

Deep Graph Infomax

Petar Veličković

William Fedus

William L. Hamilton

Pietro Lio

(Rex) Devon Hjelm

We present Deep Graph Infomax (DGI), a general approach for learning node representations within graph-structured data in an unsupervised ma… (see more)nner. DGI relies on maximizing mutual information between patch representations and corresponding high-level summaries of graphs---both derived using established graph convolutional network architectures. The learnt patch representations summarize subgraphs centered around nodes of interest, and can thus be reused for downstream node-wise learning tasks. In contrast to most prior approaches to unsupervised learning with GCNs, DGI does not rely on random walk objectives, and is readily applicable to both transductive and inductive learning setups. We demonstrate competitive performance on a variety of node classification benchmarks, which at times even exceeds the performance of supervised learning.

2019-01-01

ICLR (Poster) (published)

Deep Graph Infomax

Petar Veličković

William Fedus

William L. Hamilton

Pietro Lio

(Rex) Devon Hjelm

2019-01-01

ICLR.cc/2019/Conference (poster)