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

Fondateur et Conseiller scientifique, Équipe de direction

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.

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

Three Factors Influencing Minima in SGD

Stanisław Jastrzębski

Amos Storkey

We study the statistical properties of the endpoint of stochastic gradient descent (SGD). We approximate SGD as a stochastic differential eq… (voir plus)uation (SDE) and consider its Boltzmann Gibbs equilibrium distribution under the assumption of isotropic variance in loss gradients.. Through this analysis, we find that three factors – learning rate, batch size and the variance of the loss gradients – control the trade-off between the depth and width of the minima found by SGD, with wider minima favoured by a higher ratio of learning rate to batch size. In the equilibrium distribution only the ratio of learning rate to batch size appears, implying that it’s invariant under a simultaneous rescaling of each by the same amount. We experimentally show how learning rate and batch size affect SGD from two perspectives: the endpoint of SGD and the dynamics that lead up to it. For the endpoint, the experiments suggest the endpoint of SGD is similar under simultaneous rescaling of batch size and learning rate, and also that a higher ratio leads to flatter minima, both findings are consistent with our theoretical analysis. We note experimentally that the dynamics also seem to be similar under the same rescaling of learning rate and batch size, which we explore showing that one can exchange batch size and learning rate in a cyclical learning rate schedule. Next, we illustrate how noise affects memorization, showing that high noise levels lead to better generalization. Finally, we find experimentally that the similarity under simultaneous rescaling of learning rate and batch size breaks down if the learning rate gets too large or the batch size gets too small.

2017-11-12

ArXiv (prépublication)

Sparse Attentive Backtracking: Long-Range Credit Assignment in Recurrent Networks

Nan Rosemary Ke

Laurent Charlin

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.

2017-11-06

ArXiv (prépublication)

Graph Attention Networks

Petar Veličković

Guillem Cucurull

Arantxa Casanova

Adriana Romero

Pietro Lio

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self… (voir plus)-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key challenges of spectral-based graph neural networks simultaneously, and make our model readily applicable to inductive as well as transductive problems. Our GAT models have achieved or matched state-of-the-art results across four established transductive and inductive graph benchmarks: the Cora, Citeseer and Pubmed citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs remain unseen during training).

2017-10-29

ArXiv (prépublication)

Learning Independent Features with Adversarial Nets for Non-linear ICA

Philemon Brakel

Reliable measures of statistical dependence could potentially be useful tools for learning independent features and performing tasks like so… (voir plus)urce separation using Independent Component Analysis (ICA). Unfortunately, many of such measures, like the mutual information, are hard to estimate and optimize directly. We propose to learn independent features with adversarial objectives (Goodfellow et al. 2014, Arjovsky et al. 2017) which optimize such measures implicitly. These objectives compare samples from the joint distribution and the product of the marginals without the need to compute any probability densities. We also propose two methods for obtaining samples from the product of the marginals using either a simple resampling trick or a separate parametric distribution. Our experiments show that this strategy can easily be applied to different types of model architectures and solve both linear and non-linear ICA problems.

2017-10-12

ArXiv (prépublication)

The Consciousness Prior

A new prior is proposed for learning representations of high-level concepts of the kind we manipulate with language. This prior can be combi… (voir plus)ned with other priors in order to help disentangling abstract factors from each other. It is inspired by cognitive neuroscience theories of consciousness, seen as a bottleneck through which just a few elements, after having been selected by attention from a broader pool, are then broadcast and condition further processing, both in perception and decision-making. The set of recently selected elements one becomes aware of is seen as forming a low-dimensional conscious state. This conscious state is combining the few concepts constituting a conscious thought, i.e., what one is immediately conscious of at a particular moment. We claim that this architectural and information-processing constraint corresponds to assumptions about the joint distribution between high-level concepts. To the extent that these assumptions are generally true (and the form of natural language seems consistent with them), they can form a useful prior for representation learning. A low-dimensional thought or conscious state is analogous to a sentence: it involves only a few variables and yet can make a statement with very high probability of being true. This is consistent with a joint distribution (over high-level concepts) which has the form of a sparse factor graph, i.e., where the dependencies captured by each factor of the factor graph involve only very few variables while creating a strong dip in the overall energy function. The consciousness prior also makes it natural to map conscious states to natural language utterances or to express classical AI knowledge in a form similar to facts and rules, albeit capturing uncertainty as well as efficient search mechanisms implemented by attention mechanisms.

2017-09-24

ArXiv (prépublication)

A Deep Reinforcement Learning Chatbot

Iulian V. Serban

Chinnadhurai Sankar

Mathieu Germain

Sandeep Subramanian

Michael Pieper

Nan Rosemary Ke

Sai Mudumba

Alexandre De Brébisson

Jose M. R. Sotelo

Vincent Michalski

Alexandre Nguyen

We present MILABOT: a deep reinforcement learning chatbot developed by the Montreal Institute for Learning Algorithms (MILA) for the Amazon … (voir plus)Alexa Prize competition. MILABOT is capable of conversing with humans on popular small talk topics through both speech and text. The system consists of an ensemble of natural language generation and retrieval models, including template-based models, bag-of-words models, sequence-to-sequence neural network and latent variable neural network models. By applying reinforcement learning to crowdsourced data and real-world user interactions, the system has been trained to select an appropriate response from the models in its ensemble. The system has been evaluated through A/B testing with real-world users, where it performed significantly better than many competing systems. Due to its machine learning architecture, the system is likely to improve with additional data.

2017-09-06

ArXiv (prépublication)

On integrating a language model into neural machine translation

Caglar Gulçehre

2017-08-31

Computer Speech and Language (publié)

Multi-way, multilingual neural machine translation

Baskaran Sankaran

F. Yarman-Vural

2017-08-31

Computer Speech and Language (publié)

Twin Networks: Using the Future as a Regularizer

Dmitriy Serdyuk

Nan Rosemary Ke

Alessandro Sordoni

Christopher Pal

Being able to model long-term dependencies in sequential data, such as text, has been among the long-standing challenges of recurrent neural… (voir plus) networks (RNNs). This issue is strictly related to the absence of explicit planning in current RNN architectures. More explicitly, the RNNs are trained to predict only the next token given previous ones. In this paper, we introduce a simple way of encouraging the RNNs to plan for the future. In order to accomplish this, we introduce an additional neural network which is trained to generate the sequence in reverse order, and we require closeness between the states of the forward RNN and backward RNN that predict the same token. At each step, the states of the forward RNN are required to match the future information contained in the backward states. We hypothesize that the approach eases modeling of long-term dependencies thus helping in generating more globally consistent samples. The model trained with conditional generation for a speech recognition task achieved 12\% relative improvement (CER of 6.7 compared to a baseline of 7.6).

2017-08-21

ArXiv (prépublication)

Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition

Layer normalization is a recently introduced technique for normalizing the activities of neurons in deep neural networks to improve the trai… (voir plus)ning speed and stability. In this paper, we introduce a new layer normalization technique called Dynamic Layer Normalization (DLN) for adaptive neural acoustic modeling in speech recognition. By dynamically generating the scaling and shifting parameters in layer normalization, DLN adapts neural acoustic models to the acoustic variability arising from various factors such as speakers, channel noises, and environments. Unlike other adaptive acoustic models, our proposed approach does not require additional adaptation data or speaker information such as i-vectors. Moreover, the model size is fixed as it dynamically generates adaptation parameters. We apply our proposed DLN to deep bidirectional LSTM acoustic models and evaluate them on two benchmark datasets for large vocabulary ASR experiments: WSJ and TED-LIUM release 2. The experimental results show that our DLN improves neural acoustic models in terms of transcription accuracy by dynamically adapting to various speakers and environments.

2017-08-19

Interspeech 2017 (publié)

Improving Speech Recognition by Revising Gated Recurrent Units

Mirco Ravanaelli

Philemon Brakel

Maurizio Omologo

Speech recognition is largely taking advantage of deep learning, showing that substantial benefits can be obtained by modern Recurrent Neura… (voir plus)l Networks (RNNs). The most popular RNNs are Long Short-Term Memory (LSTMs), which typically reach state-of-the-art performance in many tasks thanks to their ability to learn long-term dependencies and robustness to vanishing gradients. Nevertheless, LSTMs have a rather complex design with three multiplicative gates, that might impair their efficient implementation. An attempt to simplify LSTMs has recently led to Gated Recurrent Units (GRUs), which are based on just two multiplicative gates. This paper builds on these efforts by further revising GRUs and proposing a simplified architecture potentially more suitable for speech recognition. The contribution of this work is two-fold. First, we suggest to remove the reset gate in the GRU design, resulting in a more efficient single-gate architecture. Second, we propose to replace tanh with ReLU activations in the state update equations. Results show that, in our implementation, the revised architecture reduces the per-epoch training time with more than 30% and consistently improves recognition performance across different tasks, input features, and noisy conditions when compared to a standard GRU.

2017-08-19

Interspeech 2017 (publié)

Plan, Attend, Generate: Character-Level Neural Machine Translation with Planning

Caglar Gulçehre

Adam Trischler

We investigate the integration of a planning mechanism into an encoder-decoder architecture with attention. We develop a model that can plan… (voir plus) ahead when it computes alignments between the source and target sequences not only for a single time-step but for the next k time-steps as well by constructing a matrix of proposed future alignments and a commitment vector that governs whether to follow or recompute the plan. This mechanism is inspired by strategic attentive reader and writer (STRAW) model, a recent neural architecture for planning with hierarchical reinforcement learning that can also learn higher level temporal abstractions. Our proposed model is end-to-end trainable with differentiable operations. We show that our model outperforms strong baselines on character-level translation task from WMT’15 with fewer parameters and computes alignments that are qualitatively intuitive.

2017-07-31

Proceedings of the 2nd Workshop on Representation Learning for NLP (publié)