Hugo Larochelle

hugo.larochelle@mila.quebec

Directeur scientifique, Équipe de direction

Professeur associé, Université de Montréal, Département d'informatique et de recherche opérationnelle

Professeur associé, McGill University, École d'informatique

Sujets de recherche

Apprentissage profond

Google Scholar

Biographie

Hugo Larochelle est un chercheur pionnier en apprentissage profond, leader industriel et philanthrope.

Il a commencé son parcours académique auprès de deux des « Pères fondateurs » de l'intelligence artificielle : Yoshua Bengio, son directeur de thèse à l'Université de Montréal, et Geoffrey Hinton, son superviseur postdoctoral à l'Université de Toronto.

Au fil des ans, ses recherches ont mené à plusieurs découvertes majeures présentes dans les systèmes d'IA modernes. Ses travaux sur les auto-encodeurs débruiteurs (denoising autoencoders) ont identifié la reconstruction de données brutes à partir de versions corrompues comme un paradigme clé pour l'apprentissage de représentations abstraites utiles à partir de grandes quantités de données non étiquetées. Avec des modèles tels que l'estimateur de distribution autorégressif neuronal (neural autoregressive distribution estimator) et l'auto-encodeur masqué pour l'estimation de distribution (masked autoencoder distribution estimator), il a contribué à populariser la modélisation autorégressive avec des réseaux de neurones, un paradigme aujourd'hui omniprésent dans l'IA générative. Ses travaux sur l'apprentissage de nouvelles tâches sans données (Zero-Data Learning of New Tasks) ont introduit pour la première fois le concept aujourd'hui courant d'apprentissage zero-shot.

Il a ensuite transposé son expertise académique à l'industrie en cofondant la startup Whetlab, qui a été rachetée par Twitter en 2015. Après avoir travaillé chez Twitter Cortex, il a été recruté pour diriger le laboratoire de recherche en IA de Google à Montréal (Google Brain), maintenant intégré à Google DeepMind. Il est maintenant professeur associé à l'Université de Montréal et à l'Université McGill. Il a également développé une série de cours en ligne gratuits sur l’apprentissage automatique.

Père de quatre enfants, Hugo Larochelle et sa conjointe, Angèle St-Pierre, ont également fait de multiples dons à l'Université de Montréal, à l'Université de Sherbrooke (où il a été professeur) et l’Université Laval pour soutenir les étudiantes et étudiants et faire avancer la recherche, particulièrement dans le domaine de l'IA pour l’environnement. Il a également initié la conférence TechAide, qui mobilise la communauté technologique de Montréal pour amasser des fonds pour Centraide, soutenant ainsi la mission de l'organisme de bienfaisance de lutter contre la pauvreté et l'exclusion sociale.

Étudiants actuels

Sangnie Bhardwaj

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Guillaume Lajoie

Mélisande Astrid Crystal Teng

Doctorat - UdeM

Superviseur⋅e principal⋅e :

Postdoctorat - Polytechnique

Superviseur⋅e principal⋅e :

Publications

InfoBot: Structured Exploration in ReinforcementLearning Using Information Bottleneck

D. Strouse

Matthew Botvinick

Sergey Levine

InfoBot: Transfer and Exploration via the Information Bottleneck

DJ Strouse

Matthew Botvinick

Sergey Levine

A central challenge in reinforcement learning is discovering effective policies for tasks where rewards are sparsely distributed. We postula… (voir plus)te that in the absence of useful reward signals, an effective exploration strategy should seek out {\it decision states}. These states lie at critical junctions in the state space from where the agent can transition to new, potentially unexplored regions. We propose to learn about decision states from prior experience. By training a goal-conditioned policy with an information bottleneck, we can identify decision states by examining where the model actually leverages the goal state. We find that this simple mechanism effectively identifies decision states, even in partially observed settings. In effect, the model learns the sensory cues that correlate with potential subgoals. In new environments, this model can then identify novel subgoals for further exploration, guiding the agent through a sequence of potential decision states and through new regions of the state space.

2019-01-01

ICLR.cc/2019/Conference (poster)

openreview.net

Recall Traces: Backtracking Models for Efficient Reinforcement Learning

Anirudh Goyal

Philemon Brakel

William Fedus

Soumye Singhal

Timothy P. Lillicrap

Sergey Levine

Hugo Larochelle

Yoshua Bengio

In many environments only a tiny subset of all states yield high reward. In these cases, few of the interactions with the environment provid… (voir plus)e a relevant learning signal. Hence, we may want to preferentially train on those high-reward states and the probable trajectories leading to them. To this end, we advocate for the use of a backtracking model that predicts the preceding states that terminate at a given high-reward state. We can train a model which, starting from a high value state (or one that is estimated to have high value), predicts and sample for which the (state, action)-tuples may have led to that high value state. These traces of (state, action) pairs, which we refer to as Recall Traces, sampled from this backtracking model starting from a high value state, are informative as they terminate in good states, and hence we can use these traces to improve a policy. We provide a variational interpretation for this idea and a practical algorithm in which the backtracking model samples from an approximate posterior distribution over trajectories which lead to large rewards. Our method improves the sample efficiency of both on- and off-policy RL algorithms across several environments and tasks.

2019-01-01

ICLR.cc/2019/Conference (poster)

openreview.net

Blindfold Baselines for Embodied QA

We explore blindfold (question-only) baselines for Embodied Question Answering. The EmbodiedQA task requires an agent to answer a question b… (voir plus)y intelligently navigating in a simulated environment, gathering necessary visual information only through first-person vision before finally answering. Consequently, a blindfold baseline which ignores the environment and visual information is a degenerate solution, yet we show through our experiments on the EQAv1 dataset that a simple question-only baseline achieves state-of-the-art results on the EmbodiedQA task in all cases except when the agent is spawned extremely close to the object.

2018-11-12

ArXiv (prépublication)

arxiv.org

HoME: a Household Multimodal Environment

Simon Brodeur

Luca Celotti

Jean Rouat

We introduce HoME: a Household Multimodal Environment for artificial agents to learn from vision, audio, semantics, physics, and interaction… (voir plus) with objects and other agents, all within a realistic context. HoME integrates over 45,000 diverse 3D house layouts based on the SUNCG dataset, a scale which may facilitate learning, generalization, and transfer. HoME is an open-source, OpenAI Gym-compatible platform extensible to tasks in reinforcement learning, language grounding, sound-based navigation, robotics, multi-agent learning, and more. We hope HoME better enables artificial agents to learn as humans do: in an interactive, multimodal, and richly contextualized setting.

2018-01-01

ICLR (Workshop) (publié)

openreview.net

GuessWhat?! Visual Object Discovery through Multi-modal Dialogue

Olivier Pietquin

We introduce GuessWhat?!, a two-player guessing game as a testbed for research on the interplay of computer vision and dialogue systems. The… (voir plus) goal of the game is to locate an unknown object in a rich image scene by asking a sequence of questions. Higher-level image understanding, like spatial reasoning and language grounding, is required to solve the proposed task. Our key contribution is the collection of a large-scale dataset consisting of 150K human-played games with a total of 800K visual question-answer pairs on 66K images. We explain our design decisions in collecting the dataset and introduce the oracle and questioner tasks that are associated with the two players of the game. We prototyped deep learning models to establish initial baselines of the introduced tasks.

2017-07-21

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (publié)

doi.org

arxiv.org

Modulating early visual processing by language

Jérémie Mary

Olivier Pietquin

It is commonly assumed that language refers to high-level visual concepts while leaving low-level visual processing unaffected. This view do… (voir plus)minates the current literature in computational models for language-vision tasks, where visual and linguistic input are mostly processed independently before being fused into a single representation. In this paper, we deviate from this classic pipeline and propose to modulate the \emph{entire visual processing} by linguistic input. Specifically, we condition the batch normalization parameters of a pretrained residual network (ResNet) on a language embedding. This approach, which we call MOdulated RESnet (\MRN), significantly improves strong baselines on two visual question answering tasks. Our ablation study shows that modulating from the early stages of the visual processing is beneficial.

2017-07-02

ArXiv (prépublication)

arxiv.org

Movie Description

Anna Rohrbach

Atousa Torabi

Marcus Rohrbach

Niket Tandon

Chris Pal

Hugo Larochelle

Aaron Courville

Bernt Schiele

2017-01-25

International Journal of Computer Vision (publié)

doi.org

arxiv.org

Brain tumor segmentation with Deep Neural Networks

Pierre-Marc Jodoin

2017-01-01

Medical Image Analysis (publié)

doi.org

arxiv.org

Modulating early visual processing by language

Jérémie Mary

Olivier Pietquin

Zoneout: Regularizing RNNs by Randomly Preserving Hidden Activations

J'anos Kram'ar

Nan Rosemary Ke

We propose zoneout, a novel method for regularizing RNNs. At each timestep, zoneout stochastically forces some hidden units to maintain thei… (voir plus)r previous values. Like dropout, zoneout uses random noise to train a pseudo-ensemble, improving generalization. But by preserving instead of dropping hidden units, gradient information and state information are more readily propagated through time, as in feedforward stochastic depth networks. We perform an empirical investigation of various RNN regularizers, and find that zoneout gives significant performance improvements across tasks. We achieve competitive results with relatively simple models in character- and word-level language modelling on the Penn Treebank and Text8 datasets, and combining with recurrent batch normalization yields state-of-the-art results on permuted sequential MNIST.

2016-06-03

ArXiv (prépublication)

arxiv.org

Movie Description

Anna Rohrbach

Atousa Torabi

Marcus Rohrbach

Niket Tandon

Chris Pal

Hugo Larochelle

Aaron Courville

Bernt Schiele

Audio description (AD) provides linguistic descriptions of movies and allows visually impaired people to follow a movie along with their pee… (voir plus)rs. Such descriptions are by design mainly visual and thus naturally form an interesting data source for computer vision and computational linguistics. In this work we propose a novel dataset which contains transcribed ADs, which are temporally aligned to full length movies. In addition we also collected and aligned movie scripts used in prior work and compare the two sources of descriptions. We introduce the Large Scale Movie Description Challenge (LSMDC) which contains a parallel corpus of 128,118 sentences aligned to video clips from 200 movies (around 150 h of video in total). The goal of the challenge is to automatically generate descriptions for the movie clips. First we characterize the dataset by benchmarking different approaches for generating video descriptions. Comparing ADs to scripts, we find that ADs are more visual and describe precisely what is shown rather than what should happen according to the scripts created prior to movie production. Furthermore, we present and compare the results of several teams who participated in the challenges organized in the context of two workshops at ICCV 2015 and ECCV 2016.

2016-05-12

ArXiv (prépublication)

doi.org

arxiv.org

Conférence d'ouverture | Créer une IA plus sécuritaire pour la santé mentale des jeunes

TRAIL : IA responsable pour les professionnels et les leaders

Fondateur en résidence Mila Ventures

Éclaireurs autochtones en IA

Hugo Larochelle

Biographie

Étudiants actuels

Publications

Conférence d'ouverture | Créer une IA plus sécuritaire pour la santé mentale des jeunes

TRAIL : IA responsable pour les professionnels et les leaders

Fondateur en résidence Mila Ventures

Éclaireurs autochtones en IA

Mots-clés populaires:

Hugo Larochelle

Biographie

Étudiants actuels

Publications