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

Berkes Anaïs

Collaborating researcher - Cambridge University

Rim Assouel

PhD - Université de Montréal

Stefan Bauer

Independent visiting researcher

Paul Bertin

PhD - Université de Montréal

Oussama Boussif

PhD - Université de Montréal

Collaborating researcher - N/A

Xiaoyin Chen

PhD - Université de Montréal

Sanghyeok Choi

Collaborating researcher - KAIST

PhD - Université de Montréal

PhD - Université de Montréal

Research Intern - Université de Montréal

Eric Elmoznino

PhD - Université de Montréal

PhD - Université de Montréal

Léna Ezzine

PhD - Université de Montréal

Jean-Pierre Falet

PhD - Université de Montréal

Leo Feng

PhD - Université de Montréal

leo.feng@mila.quebec

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

PhD - Université de Montréal

Collaborating Alumni - Université de Montréal

Minsu Kim

Research Intern - Université de Montréal

Hyeonah Kim

Postdoctorate - Université de Montréal

Yaroslav KIVVA

Collaborating researcher - Université de Montréal

Salem Lahlou

Collaborating Alumni - Université de Montréal

Seanie Lee

Collaborating Alumni - Université de Montréal

Postdoctorate - Université de Montréal

Collaborating Alumni

Zhen Liu

Collaborating Alumni - Université de Montréal

Kanika Madan

PhD - Université de Montréal

Nikolay Malkin

Collaborating Alumni - Université de Montréal

Cristian Dragos Manta

PhD - Université de Montréal

Sören Mindermann

Collaborating researcher - Université de Montréal

Sarthak Mittal

PhD - Université de Montréal

PhD - Université de Montréal

Postdoctorate - Université de Montréal

Independent visiting researcher - Université de Montréal

Padideh Nouri

PhD - Université de Montréal

Ali Parviz

Collaborating researcher - Ying Wu Coll of Computing

Lena Podina

PhD - University of Waterloo

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

Victor Schmidt

Collaborating Alumni - Université de Montréal

Postdoctorate - Université de Montréal

Master's Research - Université de Montréal

Marcin Sendera

Collaborating Alumni - 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

Vincent Taboga

Postdoctorate - Polytechnique Montréal

Mélisande Astrid Crystal Teng

PhD - Université de Montréal

alexander.tong@mila.quebec

Alex Tong

Postdoctorate - Université de Montréal

Postdoctorate - Université de Montréal

PhD - Université de Montréal

PhD - Université de Montréal

Leah WAIRIMU

Collaborating researcher - Université de Montréal

Omar G. Younis

Collaborating researcher

Collaborating researcher - KAIST

Nicole Zhang

PhD - McGill University

Dinghuai Zhang

PhD - Université de Montréal

Tianyu Zhang

PhD - Université de Montréal

Harry Zhao

PhD - McGill University

Skipper: Combining Spatial and Temporal Abstraction for Better Generalization

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

Fraternal Dropout

Konrad Żołna

Devansh Arpit

Dendi Suhubdy

Recurrent neural networks (RNNs) are important class of architectures among neural networks useful for language modeling and sequential pred… (see more)iction. However, optimizing RNNs is known to be harder compared to feed-forward neural networks. A number of techniques have been proposed in literature to address this problem. In this paper we propose a simple technique called fraternal dropout that takes advantage of dropout to achieve this goal. Specifically, we propose to train two identical copies of an RNN (that share parameters) with different dropout masks while minimizing the difference between their (pre-softmax) predictions. In this way our regularization encourages the representations of RNNs to be invariant to dropout mask, thus being robust. We show that our regularization term is upper bounded by the expectation-linear dropout objective which has been shown to address the gap due to the difference between the train and inference phases of dropout. We evaluate our model and achieve state-of-the-art results in sequence modeling tasks on two benchmark datasets - Penn Treebank and Wikitext-2. We also show that our approach leads to performance improvement by a significant margin in image captioning (Microsoft COCO) and semi-supervised (CIFAR-10) tasks.

2018-01-01

ICLR (Poster) (published)

Fraternal Dropout

Konrad Żołna

Devansh Arpit

Dendi Suhubdy

2018-01-01

ICLR.cc/2018/Conference (poster)

Graph Attention Networks

Petar Veličković

Guillem Cucurull

Arantxa Casanova

Adriana Romero Soriano

Pietro Lio

2018-01-01

ICLR.cc/2018/Conference (poster)

Image-to-image translation for cross-domain disentanglement

Abel Gonzalez-Garcia

Joost van de Weijer

Deep image translation methods have recently shown excellent results, outputting high-quality images covering multiple modes of the data dis… (see more)tribution. There has also been increased interest in disentangling the internal representations learned by deep methods to further improve their performance and achieve a finer control. In this paper, we bridge these two objectives and introduce the concept of cross-domain disentanglement. We aim to separate the internal representation into three parts. The shared part contains information for both domains. The exclusive parts, on the other hand, contain only factors of variation that are particular to each domain. We achieve this through bidirectional image translation based on Generative Adversarial Networks and cross-domain autoencoders, a novel network component. Our model offers multiple advantages. We can output diverse samples covering multiple modes of the distributions of both domains, perform domain-specific image transfer and interpolation, and cross-domain retrieval without the need of labeled data, only paired images. We compare our model to the state-of-the-art in multi-modal image translation and achieve better results for translation on challenging datasets as well as for cross-domain retrieval on realistic datasets.

LATTER M INIMA WITH SGD

Stanisław Jastrzębski

Zac Kenton

Devansh Arpit

Nicolas Ballas

Asja Fischer

Amos Storkey

It has been discussed that over-parameterized deep neural networks (DNNs) trained using stochastic gradient descent (SGD) with smaller batch… (see more) sizes generalize better compared with those trained with larger batch sizes. Additionally, model parameters found by small batch size SGD tend to be in flatter regions. We extend these empirical observations and experimentally show that both large learning rate and small batch size contribute towards SGD finding flatter minima that generalize well. Conversely, we find that small learning rates and large batch sizes lead to sharper minima that correlate with poor generalization in DNNs.

2018-01-01

(published)

www.semanticscholar.org

LATTER M INIMA WITH SGD

Stanisław Jastrzębski

Zac Kenton

Devansh Arpit

Nicolas Ballas

Asja Fischer

Amos Storkey

Learning General Purpose Distributed Sentence Representations via Large Scale Multi-task Learning

Sandeep Subramanian

Adam Trischler

Chris Pal

A lot of the recent success in natural language processing (NLP) has been driven by distributed vector representations of words trained on l… (see more)arge amounts of text in an unsupervised manner. These representations are typically used as general purpose features for words across a range of NLP problems. However, extending this success to learning representations of sequences of words, such as sentences, remains an open problem. Recent work has explored unsupervised as well as supervised learning techniques with different training objectives to learn general purpose fixed-length sentence representations. In this work, we present a simple, effective multi-task learning framework for sentence representations that combines the inductive biases of diverse training objectives in a single model. We train this model on several data sources with multiple training objectives on over 100 million sentences. Extensive experiments demonstrate that sharing a single recurrent sentence encoder across weakly related tasks leads to consistent improvements over previous methods. We present substantial improvements in the context of transfer learning and low-resource settings using our learned general-purpose representations.

2018-01-01

ICLR (Poster) (published)

MetaGAN: An Adversarial Approach to Few-Shot Learning

Ruixiang ZHANG

Tong Che

Zoubin Ghahramani

Yangqiu Song

In this paper, we propose a conceptually simple and general framework called MetaGAN for few-shot learning problems. Most state-of-the-art f… (see more)ew-shot classification models can be integrated with MetaGAN in a principled and straightforward way. By introducing an adversarial generator conditioned on tasks, we augment vanilla few-shot classification models with the ability to discriminate between real and fake data. We argue that this GAN-based approach can help few-shot classifiers to learn sharper decision boundary, which could generalize better. We show that with our MetaGAN framework, we can extend supervised few-shot learning models to naturally cope with unlabeled data. Different from previous work in semi-supervised few-shot learning, our algorithms can deal with semi-supervision at both sample-level and task-level. We give theoretical justifications of the strength of MetaGAN, and validate the effectiveness of MetaGAN on challenging few-shot image classification benchmarks.

Sparse Attentive Backtracking: Temporal CreditAssignment Through Reminding

Nan Rosemary Ke

Anirudh Goyal

Olexa Bilaniuk

Jonathan Binas

Michael Curtis Mozer

Chris Pal

Learning long-term dependencies in extended temporal sequences requires credit assignment to events far back in the past. The most common me… (see more)thod for training recurrent neural networks, back-propagation through time (BPTT), requires credit information to be propagated backwards through every single step of the forward computation, potentially over thousands or millions of time steps. This becomes computationally expensive or even infeasible when used with long sequences. Importantly, biological brains are unlikely to perform such detailed reverse replay over very long sequences of internal states (consider days, months, or years.) However, humans are often reminded of past memories or mental states which are associated with the current mental state. We consider the hypothesis that such memory associations between past and present could be used for credit assignment through arbitrarily long sequences, propagating the credit assigned to the current state to the associated past state. Based on this principle, we study a novel algorithm which only back-propagates through a few of these temporal skip connections, realized by a learned attention mechanism that associates current states with relevant past states. We demonstrate in experiments that our method matches or outperforms regular BPTT and truncated BPTT in tasks involving particularly long-term dependencies, but without requiring the biologically implausible backward replay through the whole history of states. Additionally, we demonstrate that the proposed method transfers to longer sequences significantly better than LSTMs trained with BPTT and LSTMs trained with full self-attention.

Twin Networks: Matching the Future for Sequence Generation

Dmitriy Serdyuk

Nan Rosemary Ke

Alessandro Sordoni

Adam Trischler

Chris Pal

We propose a simple technique for encouraging generative RNNs to plan ahead. We train a "backward" recurrent network to generate a given seq… (see more)uence in reverse order, and we encourage states of the forward model to predict cotemporal states of the backward model. The backward network is used only during training, and plays no role during sampling or inference. We hypothesize that our approach eases modeling of long-term dependencies by implicitly forcing the forward states to hold information about the longer-term future (as contained in the backward states). We show empirically that our approach achieves 9% relative improvement for a speech recognition task, and achieves significant improvement on a COCO caption generation task.

2018-01-01

ICLR (Poster) (published)

Universal Successor Representations for Transfer Reinforcement Learning

Chen Ma

Junfeng Wen

The objective of transfer reinforcement learning is to generalize from a set of previous tasks to unseen new tasks. In this work, we focus o… (see more)n the transfer scenario where the dynamics among tasks are the same, but their goals differ. Although general value function (Sutton et al., 2011) has been shown to be useful for knowledge transfer, learning a universal value function can be challenging in practice. To attack this, we propose (1) to use universal successor representations (USR) to represent the transferable knowledge and (2) a USR approximator (USRA) that can be trained by interacting with the environment. Our experiments show that USR can be effectively applied to new tasks, and the agent initialized by the trained USRA can achieve the goal considerably faster than random initialization.

2018-01-01

ICLR (Workshop) (published)

Dendritic error backpropagation in deep cortical microcircuits

João Sacramento

Rui Ponte Costa

Walter Senn

Animal behaviour depends on learning to associate sensory stimuli with the desired motor command. Understanding how the brain orchestrates t… (see more)he necessary synaptic modifications across different brain areas has remained a longstanding puzzle. Here, we introduce a multi-area neuronal network model in which synaptic plasticity continuously adapts the network towards a global desired output. In this model synaptic learning is driven by a local dendritic prediction error that arises from a failure to predict the top-down input given the bottom-up activities. Such errors occur at apical dendrites of pyramidal neurons where both long-range excitatory feedback and local inhibitory predictions are integrated. When local inhibition fails to match excitatory feedback an error occurs which triggers plasticity at bottom-up synapses at basal dendrites of the same pyramidal neurons. We demonstrate the learning capabilities of the model in a number of tasks and show that it approximates the classical error backpropagation algorithm. Finally, complementing this cortical circuit with a disinhibitory mechanism enables attention-like stimulus denoising and generation. Our framework makes several experimental predictions on the function of dendritic integration and cortical microcircuits, is consistent with recent observations of cross-area learning, and suggests a biological implementation of deep learning.

2017-12-30

ArXiv (preprint)