Yoshua Bengio

Biography

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

For more information please contact Cassidy MacNeil, Senior Assistant and Operation Lead at cassidy.macneil@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

Berkes Anaïs

Collaborating researcher - Cambridge University

Principal supervisor :

Rim Assouel

PhD - Université de Montréal

Stefan Bauer

Independent visiting researcher

Co-supervisor :

Guillaume Lajoie

Shahana Chatterjee

Collaborating researcher - N/A

Principal supervisor :

PhD - Université de Montréal

Sanghyeok Choi

Collaborating researcher - KAIST

PhD - Université de Montréal

Collaborating Alumni - Université de Montréal

Co-supervisor :

Loubna Benabbou

Desmond Elliott

Independent visiting researcher

Principal supervisor :

PhD - Université de Montréal

Co-supervisor :

PhD - Université de Montréal

Jean-Pierre Falet

PhD - Université de Montréal

PhD

PhD - Université de Montréal

Moksh Jain

PhD - Université de Montréal

PhD - Université de Montréal

Principal supervisor :

Collaborating Alumni - Université de Montréal

Hyeonah Kim

Postdoctorate - Université de Montréal

Principal supervisor :

Alex Hernández-García

Tabitha Edith Lee

Postdoctorate - Université de Montréal

Principal supervisor :

Collaborating Alumni

Collaborating Alumni - Université de Montréal

Cristian Dragos Manta

PhD - Université de Montréal

Co-supervisor :

Dhanya Sridhar

Sarthak Mittal

PhD - 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

Collaborating researcher - University of Waterloo

Principal supervisor :

David Rolnick

Nassim Rahaman

Collaborating Alumni - Max-Planck-Institute for Intelligent Systems

Amine RAZIG

Collaborating researcher - Université de Montréal

Co-supervisor :

Loubna Benabbou

Jarrid Rector-Brooks

PhD - Université de Montréal

Danyal REHMAN

Postdoctorate - Université de Montréal

Oli RICHARDSON

Postdoctorate - Université de Montréal

Camille Rochefort-Boulanger

PhD - Université de Montréal

Principal supervisor :

Julie Hussin

Dragos Secrieru

Collaborating Alumni - Université de Montréal

Divya Sharma

Postdoctorate

Co-supervisor :

Alex Hernández-García

Mélisande Astrid Crystal Teng

Vincent Taboga

Collaborating Alumni - Polytechnique Montréal

Co-supervisor :

PhD - Université de Montréal

Co-supervisor :

Hugo Larochelle

Ivan Titov

Collaborating researcher

Principal supervisor :

Siva Reddy

Alex Tong

Collaborating Alumni - Université de Montréal

Collaborating Alumni - Université de Montréal

Co-supervisor :

PhD - Université de Montréal

Principal supervisor :

Collaborating researcher

Collaborating researcher - Université de Montréal

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

Collaborating Alumni - 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

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.

2019-03-19

arXiv.org (preprint)

dblp.uni-trier.de

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… (see more)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.

2019-03-16

bioRxiv (preprint)

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.

2019-03-04

ArXiv (preprint)

arxiv.org

Hyperbolic Discounting and Learning over Multiple Horizons

William Fedus

Carles Gelada

Bellemare Marc-Emmanuel

Hugo Larochelle

Reinforcement learning (RL) typically defines a discount factor as part of the Markov Decision Process. The discount factor values future re… (see more)wards by an exponential scheme that leads to theoretical convergence guarantees of the Bellman equation. However, evidence from psychology, economics and neuroscience suggests that humans and animals instead have hyperbolic time-preferences. In this work we revisit the fundamentals of discounting in RL and bridge this disconnect by implementing an RL agent that acts via hyperbolic discounting. We demonstrate that a simple approach approximates hyperbolic discount functions while still using familiar temporal-difference learning techniques in RL. Additionally, and independent of hyperbolic discounting, we make a surprising discovery that simultaneously learning value functions over multiple time-horizons is an effective auxiliary task which often improves over a strong value-based RL agent, Rainbow.

2019-02-18

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.

2019-01-31

Neural Computation (published)

Maximum Entropy Generators for Energy-Based Models

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.

2019-01-23

ArXiv (preprint)

arxiv.org

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.

2019-01-10

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.

2018-12-31

ICLR.cc/2019/Conference (poster)

On Adversarial Mixup Resynthesis

R Devon Hjelm

Christopher 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.

2018-12-31

NeurIPS (published)

dblp.uni-trier.de

Artificial Intelligence Cytometer in Blood

Geoffrey Hinton

2018-12-31

(published)

www.semanticscholar.org

Avoidance Learning Using Observational Reinforcement Learning

David Venuto

Léonard Boussioux

Junhao Wang

Rola Dali

Jhelum Chakravorty

Doina Precup

Imitation learning seeks to learn an expert policy from sampled demonstrations. However, in the real world, it is often difficult to find a … (see more)perfect expert and avoiding dangerous behaviors becomes relevant for safety reasons. We present the idea of \textit{learning to avoid}, an objective opposite to imitation learning in some sense, where an agent learns to avoid a demonstrator policy given an environment. We define avoidance learning as the process of optimizing the agent's reward while avoiding dangerous behaviors given by a demonstrator. In this work we develop a framework of avoidance learning by defining a suitable objective function for these problems which involves the \emph{distance} of state occupancy distributions of the expert and demonstrator policies. We use density estimates for state occupancy measures and use the aforementioned distance as the reward bonus for avoiding the demonstrator. We validate our theory with experiments using a wide range of partially observable environments. Experimental results show that we are able to improve sample efficiency during training compared to state of the art policy optimization and safety methods.

2018-12-31

arXiv (preprint)

arxiv.org

BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning

Maxime Chevalier-Boisvert

Allowing humans to interactively train artificial agents to understand language instructions is desirable for both practical and scientific … (see more)reasons, but given the poor data efficiency of the current learning methods, this goal may require substantial research efforts. Here, we introduce the BabyAI research platform to support investigations towards including humans in the loop for grounded language learning. The BabyAI platform comprises an extensible suite of 19 levels of increasing difficulty. The levels gradually lead the agent towards acquiring a combinatorially rich synthetic language which is a proper subset of English. The platform also provides a heuristic expert agent for the purpose of simulating a human teacher. We report baseline results and estimate the amount of human involvement that would be required to train a neural network-based agent on some of the BabyAI levels. We put forward strong evidence that current deep learning methods are not yet sufficiently sample efficient when it comes to learning a language with compositional properties.

2018-12-31

ICLR.cc/2019/Conference (poster)