Search Results for author: Hugo Larochelle

Found 77 papers, 37 papers with code

Matching Feature Sets for Few-Shot Image Classification

no code implementations2 Apr 2022 Arman Afrasiyabi, Hugo Larochelle, Jean-François Lalonde, Christian Gagné

In image classification, it is common practice to train deep networks to extract a single feature vector per input image.

Classification Few-Shot Image Classification +1

Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions

1 code implementation7 Mar 2022 David Bieber, Rishab Goel, Daniel Zheng, Hugo Larochelle, Daniel Tarlow

This presents an interesting machine learning challenge: can we predict runtime errors in a "static" setting, where program execution is not possible?

Learning to Execute

Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning

1 code implementation10 Jan 2022 Utku Evci, Vincent Dumoulin, Hugo Larochelle, Michael C. Mozer

We propose a method, Head-to-Toe probing (Head2Toe), that selects features from all layers of the source model to train a classification head for the target-domain.

Transfer Learning

Head2Toe: Utilizing Intermediate Representations for Better OOD Generalization

no code implementations29 Sep 2021 Utku Evci, Vincent Dumoulin, Hugo Larochelle, Michael Curtis Mozer

We propose a method, Head-to-Toe probing (Head2Toe), that selects features from all layers of the source model to train a classification head for the target-domain.

Transfer Learning

Impact of Aliasing on Generalization in Deep Convolutional Networks

no code implementations ICCV 2021 Cristina Vasconcelos, Hugo Larochelle, Vincent Dumoulin, Rob Romijnders, Nicolas Le Roux, Ross Goroshin

We investigate the impact of aliasing on generalization in Deep Convolutional Networks and show that data augmentation schemes alone are unable to prevent it due to structural limitations in widely used architectures.

Data Augmentation Few-Shot Learning +1

Learning a Universal Template for Few-shot Dataset Generalization

1 code implementation14 May 2021 Eleni Triantafillou, Hugo Larochelle, Richard Zemel, Vincent Dumoulin

Few-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purpose of training an adaptable model that can then learn classes from new datasets using only a few examples.

Comparing Transfer and Meta Learning Approaches on a Unified Few-Shot Classification Benchmark

1 code implementation6 Apr 2021 Vincent Dumoulin, Neil Houlsby, Utku Evci, Xiaohua Zhai, Ross Goroshin, Sylvain Gelly, Hugo Larochelle

To bridge this gap, we perform a cross-family study of the best transfer and meta learners on both a large-scale meta-learning benchmark (Meta-Dataset, MD), and a transfer learning benchmark (Visual Task Adaptation Benchmark, VTAB).

Few-Shot Learning General Classification +1

Interpretable Multi-Modal Hate Speech Detection

no code implementations2 Mar 2021 Prashanth Vijayaraghavan, Hugo Larochelle, Deb Roy

With growing role of social media in shaping public opinions and beliefs across the world, there has been an increased attention to identify and counter the problem of hate speech on social media.

Hate Speech Detection

Self-Supervised Equivariant Scene Synthesis from Video

no code implementations1 Feb 2021 Cinjon Resnick, Or Litany, Cosmas Heiß, Hugo Larochelle, Joan Bruna, Kyunghyun Cho

We propose a self-supervised framework to learn scene representations from video that are automatically delineated into background, characters, and their animations.

Dependency Structure Discovery from Interventions

no code implementations1 Jan 2021 Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Bernhard Schölkopf, Michael Curtis Mozer, Hugo Larochelle, Christopher Pal, Yoshua Bengio

Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data.

Learning Flexible Classifiers with Shot-CONditional Episodic (SCONE) Training

no code implementations1 Jan 2021 Eleni Triantafillou, Vincent Dumoulin, Hugo Larochelle, Richard Zemel

We discover that fine-tuning on episodes of a particular shot can specialize the pre-trained model to solving episodes of that shot at the expense of performance on other shots, in agreement with a trade-off recently observed in the context of end-to-end episodic training.

General Classification

An Effective Anti-Aliasing Approach for Residual Networks

no code implementations20 Nov 2020 Cristina Vasconcelos, Hugo Larochelle, Vincent Dumoulin, Nicolas Le Roux, Ross Goroshin

Image pre-processing in the frequency domain has traditionally played a vital role in computer vision and was even part of the standard pipeline in the early days of deep learning.

Few-Shot Learning Image Classification +1

Learned Equivariant Rendering without Transformation Supervision

no code implementations11 Nov 2020 Cinjon Resnick, Or Litany, Hugo Larochelle, Joan Bruna, Kyunghyun Cho

We propose a self-supervised framework to learn scene representations from video that are automatically delineated into objects and background.

Learning to Execute Programs with Instruction Pointer Attention Graph Neural Networks

1 code implementation NeurIPS 2020 David Bieber, Charles Sutton, Hugo Larochelle, Daniel Tarlow

More practically, we evaluate these models on the task of learning to execute partial programs, as might arise if using the model as a heuristic function in program synthesis.

Code Completion Learning to Execute +2

On-the-Fly Adaptation of Source Code Models

no code implementations NeurIPS Workshop CAP 2020 Disha Shrivastava, Hugo Larochelle, Daniel Tarlow

The ability to adapt to unseen, local contexts is an important challenge that successful models of source code must overcome.

Revisiting Fundamentals of Experience Replay

2 code implementations ICML 2020 William Fedus, Prajit Ramachandran, Rishabh Agarwal, Yoshua Bengio, Hugo Larochelle, Mark Rowland, Will Dabney

Experience replay is central to off-policy algorithms in deep reinforcement learning (RL), but there remain significant gaps in our understanding.

DQN Replay Dataset Q-Learning +1

Learning Graph Structure With A Finite-State Automaton Layer

1 code implementation NeurIPS 2020 Daniel D. Johnson, Hugo Larochelle, Daniel Tarlow

In practice, edges are used both to represent intrinsic structure (e. g., abstract syntax trees of programs) and more abstract relations that aid reasoning for a downstream task (e. g., results of relevant program analyses).

Variable misuse

Uniform Priors for Data-Efficient Transfer

no code implementations30 Jun 2020 Samarth Sinha, Karsten Roth, Anirudh Goyal, Marzyeh Ghassemi, Hugo Larochelle, Animesh Garg

Deep Neural Networks have shown great promise on a variety of downstream applications; but their ability to adapt and generalize to new data and tasks remains a challenge.

Domain Adaptation Meta-Learning +1

Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)

no code implementations27 Mar 2020 Joelle Pineau, Philippe Vincent-Lamarre, Koustuv Sinha, Vincent Larivière, Alina Beygelzimer, Florence d'Alché-Buc, Emily Fox, Hugo Larochelle

Reproducibility, that is obtaining similar results as presented in a paper or talk, using the same code and data (when available), is a necessary step to verify the reliability of research findings.

On-the-Fly Adaptation of Source Code Models using Meta-Learning

no code implementations26 Mar 2020 Disha Shrivastava, Hugo Larochelle, Daniel Tarlow

The ability to adapt to unseen, local contexts is an important challenge that successful models of source code must overcome.

Frame Meta-Learning

Your GAN is Secretly an Energy-based Model and You Should use Discriminator Driven Latent Sampling

3 code implementations NeurIPS 2020 Tong Che, Ruixiang Zhang, Jascha Sohl-Dickstein, Hugo Larochelle, Liam Paull, Yuan Cao, Yoshua Bengio

To make that practical, we show that sampling from this modified density can be achieved by sampling in latent space according to an energy-based model induced by the sum of the latent prior log-density and the discriminator output score.

Image Generation

Diversity inducing Information Bottleneck in Model Ensembles

1 code implementation10 Mar 2020 Samarth Sinha, Homanga Bharadhwaj, Anirudh Goyal, Hugo Larochelle, Animesh Garg, Florian Shkurti

Although deep learning models have achieved state-of-the-art performance on a number of vision tasks, generalization over high dimensional multi-modal data, and reliable predictive uncertainty estimation are still active areas of research.

Out-of-Distribution Detection

Curriculum By Smoothing

1 code implementation NeurIPS 2020 Samarth Sinha, Animesh Garg, Hugo Larochelle

We propose to augment the train-ing of CNNs by controlling the amount of high frequency information propagated within the CNNs as training progresses, by convolving the output of a CNN feature map of each layer with a Gaussian kernel.

Image Classification Transfer Learning

On Catastrophic Interference in Atari 2600 Games

1 code implementation28 Feb 2020 William Fedus, Dibya Ghosh, John D. Martin, Marc G. Bellemare, Yoshua Bengio, Hugo Larochelle

Our study provides a clear empirical link between catastrophic interference and sample efficiency in reinforcement learning.

Atari Games reinforcement-learning

Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction

no code implementations28 Nov 2019 Vishal Jain, William Fedus, Hugo Larochelle, Doina Precup, Marc G. Bellemare

Empirically, we find that these techniques improve the performance of a baseline deep reinforcement learning agent applied to text-based games.

reinforcement-learning text-based games

Small-GAN: Speeding Up GAN Training Using Core-sets

no code implementations ICML 2020 Samarth Sinha, Han Zhang, Anirudh Goyal, Yoshua Bengio, Hugo Larochelle, Augustus Odena

Recent work by Brock et al. (2018) suggests that Generative Adversarial Networks (GANs) benefit disproportionately from large mini-batch sizes.

Active Learning Anomaly Detection +1

Learning Neural Causal Models from Unknown Interventions

2 code implementations2 Oct 2019 Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Hugo Larochelle, Bernhard Schölkopf, Michael C. Mozer, Chris Pal, Yoshua Bengio

Promising results have driven a recent surge of interest in continuous optimization methods for Bayesian network structure learning from observational data.

Meta-Learning

Are Few-shot Learning Benchmarks Too Simple ?

no code implementations25 Sep 2019 Gabriel Huang, Hugo Larochelle, Simon Lacoste-Julien

We argue that the widely used Omniglot and miniImageNet benchmarks are too simple because their class semantics do not vary across episodes, which defeats their intended purpose of evaluating few-shot classification methods.

Classification Few-Shot Learning

Transfer and Exploration via the Information Bottleneck

1 code implementation ICLR 2019 Anirudh Goyal, Riashat Islam, DJ Strouse, Zafarali Ahmed, Hugo Larochelle, Matthew Botvinick, Yoshua Bengio, Sergey Levine

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.

Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time

1 code implementation22 Feb 2019 Gabriel Huang, Hugo Larochelle, Simon Lacoste-Julien

We show that several popular few-shot learning benchmarks can be solved with varying degrees of success without using support set Labels at Test-time (LT).

Few-Shot Learning General Classification

InfoBot: Transfer and Exploration via the Information Bottleneck

no code implementations30 Jan 2019 Anirudh Goyal, Riashat Islam, Daniel Strouse, Zafarali Ahmed, Matthew Botvinick, Hugo Larochelle, Yoshua Bengio, Sergey Levine

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.

Language GANs Falling Short

1 code implementation ICLR 2020 Massimo Caccia, Lucas Caccia, William Fedus, Hugo Larochelle, Joelle Pineau, Laurent Charlin

Generating high-quality text with sufficient diversity is essential for a wide range of Natural Language Generation (NLG) tasks.

Text Generation

Meta-Learning for Semi-Supervised Few-Shot Classification

8 code implementations ICLR 2018 Mengye Ren, Eleni Triantafillou, Sachin Ravi, Jake Snell, Kevin Swersky, Joshua B. Tenenbaum, Hugo Larochelle, Richard S. Zemel

To address this paradigm, we propose novel extensions of Prototypical Networks (Snell et al., 2017) that are augmented with the ability to use unlabeled examples when producing prototypes.

Classification General Classification +1

A Meta-Learning Perspective on Cold-Start Recommendations for Items

no code implementations NeurIPS 2017 Manasi Vartak, Arvind Thiagarajan, Conrado Miranda, Jeshua Bratman, Hugo Larochelle

Matrix factorization (MF) is one of the most popular techniques for product recommendation, but is known to suffer from serious cold-start problems.

Meta-Learning Product Recommendation

HoME: a Household Multimodal Environment

no code implementations29 Nov 2017 Simon Brodeur, Ethan Perez, Ankesh Anand, Florian Golemo, Luca Celotti, Florian Strub, Jean Rouat, Hugo Larochelle, Aaron Courville

We introduce HoME: a Household Multimodal Environment for artificial agents to learn from vision, audio, semantics, physics, and interaction with objects and other agents, all within a realistic context.

OpenAI Gym reinforcement-learning

GuessWhat?! Visual object discovery through multi-modal dialogue

3 code implementations CVPR 2017 Harm de Vries, Florian Strub, Sarath Chandar, Olivier Pietquin, Hugo Larochelle, Aaron Courville

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.

Object Discovery

Deep learning trends for focal brain pathology segmentation in MRI

no code implementations18 Jul 2016 Mohammad Havaei, Nicolas Guizard, Hugo Larochelle, Pierre-Marc Jodoin

In this chapter, we provide a survey of CNN methods applied to medical imaging with a focus on brain pathology segmentation.

Medical Diagnosis

Hierarchical Memory Networks

no code implementations24 May 2016 Sarath Chandar, Sungjin Ahn, Hugo Larochelle, Pascal Vincent, Gerald Tesauro, Yoshua Bengio

In this paper, we explore a form of hierarchical memory network, which can be considered as a hybrid between hard and soft attention memory networks.

Hard Attention Question Answering

Movie Description

no code implementations12 May 2016 Anna Rohrbach, Atousa Torabi, Marcus Rohrbach, Niket Tandon, Christopher Pal, Hugo Larochelle, Aaron Courville, Bernt Schiele

In addition we also collected and aligned movie scripts used in prior work and compare the two sources of descriptions.

Neural Autoregressive Distribution Estimation

3 code implementations7 May 2016 Benigno Uria, Marc-Alexandre Côté, Karol Gregor, Iain Murray, Hugo Larochelle

We present Neural Autoregressive Distribution Estimation (NADE) models, which are neural network architectures applied to the problem of unsupervised distribution and density estimation.

Density Estimation Image Generation

Recurrent Mixture Density Network for Spatiotemporal Visual Attention

no code implementations27 Mar 2016 Loris Bazzani, Hugo Larochelle, Lorenzo Torresani

In this work, we propose a spatiotemporal attentional model that learns where to look in a video directly from human fixation data.

Action Classification Frame +1

Document Neural Autoregressive Distribution Estimation

no code implementations18 Mar 2016 Stanislas Lauly, Yin Zheng, Alexandre Allauzen, Hugo Larochelle

We present an approach based on feed-forward neural networks for learning the distribution of textual documents.

Autoencoding beyond pixels using a learned similarity metric

28 code implementations31 Dec 2015 Anders Boesen Lindbo Larsen, Søren Kaae Sønderby, Hugo Larochelle, Ole Winther

We present an autoencoder that leverages learned representations to better measure similarities in data space.

Translation

Dynamic Capacity Networks

1 code implementation24 Nov 2015 Amjad Almahairi, Nicolas Ballas, Tim Cooijmans, Yin Zheng, Hugo Larochelle, Aaron Courville

The low-capacity sub-networks are applied across most of the input, but also provide a guide to select a few portions of the input on which to apply the high-capacity sub-networks.

Within-Brain Classification for Brain Tumor Segmentation

no code implementations5 Oct 2015 Mohammad Havaei, Hugo Larochelle, Philippe Poulin, Pierre-Marc Jodoin

Purpose: In this paper, we investigate a framework for interactive brain tumor segmentation which, at its core, treats the problem of interactive brain tumor segmentation as a machine learning problem.

Brain Tumor Segmentation Classification +2

Clustering is Efficient for Approximate Maximum Inner Product Search

no code implementations21 Jul 2015 Alex Auvolat, Sarath Chandar, Pascal Vincent, Hugo Larochelle, Yoshua Bengio

Efficient Maximum Inner Product Search (MIPS) is an important task that has a wide applicability in recommendation systems and classification with a large number of classes.

Recommendation Systems Word Embeddings

Domain-Adversarial Training of Neural Networks

30 code implementations28 May 2015 Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, Victor Lempitsky

Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains.

Domain Generalization General Classification +4

Correlational Neural Networks

2 code implementations27 Apr 2015 Sarath Chandar, Mitesh M. Khapra, Hugo Larochelle, Balaraman Ravindran

CCA based approaches learn a joint representation by maximizing correlation of the views when projected to the common subspace.

Representation Learning Transfer Learning

Describing Videos by Exploiting Temporal Structure

5 code implementations ICCV 2015 Li Yao, Atousa Torabi, Kyunghyun Cho, Nicolas Ballas, Christopher Pal, Hugo Larochelle, Aaron Courville

In this context, we propose an approach that successfully takes into account both the local and global temporal structure of videos to produce descriptions.

Action Recognition Video Description

MADE: Masked Autoencoder for Distribution Estimation

15 code implementations12 Feb 2015 Mathieu Germain, Karol Gregor, Iain Murray, Hugo Larochelle

There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples.

Density Estimation Image Generation

An Infinite Restricted Boltzmann Machine

1 code implementation9 Feb 2015 Marc-Alexandre Côté, Hugo Larochelle

We present a mathematical construction for the restricted Boltzmann machine (RBM) that doesn't require specifying the number of hidden units.

Domain-Adversarial Neural Networks

1 code implementation15 Dec 2014 Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand

We propose a training objective that implements this idea in the context of a neural network, whose hidden layer is trained to be predictive of the classification task, but uninformative as to the domain of the input.

Denoising Domain Adaptation +3

Topic Modeling of Multimodal Data: An Autoregressive Approach

no code implementations CVPR 2014 Yin Zheng, Yu-Jin Zhang, Hugo Larochelle

Topic modeling based on latent Dirichlet allocation (LDA) has been a framework of choice to deal with multimodal data, such as in image annotation tasks.

Image Classification Topic Models

Sequential Model-Based Ensemble Optimization

no code implementations4 Feb 2014 Alexandre Lacoste, Hugo Larochelle, François Laviolette, Mario Marchand

One of the most tedious tasks in the application of machine learning is model selection, i. e. hyperparameter selection.

Model Selection

Learning Multilingual Word Representations using a Bag-of-Words Autoencoder

no code implementations8 Jan 2014 Stanislas Lauly, Alex Boulanger, Hugo Larochelle

Recent work on learning multilingual word representations usually relies on the use of word-level alignements (e. g. infered with the help of GIZA++) between translated sentences, in order to align the word embeddings in different languages.

Document Classification General Classification +2

A Deep and Tractable Density Estimator

no code implementations7 Oct 2013 Benigno Uria, Iain Murray, Hugo Larochelle

We can thus use the most convenient model for each inference task at hand, and ensembles of such models with different orderings are immediately available.

Density Estimation Image Generation

A Supervised Neural Autoregressive Topic Model for Simultaneous Image Classification and Annotation

no code implementations23 May 2013 Yin Zheng, Yu-Jin Zhang, Hugo Larochelle

Topic modeling based on latent Dirichlet allocation (LDA) has been a framework of choice to perform scene recognition and annotation.

General Classification Image Classification +2

A Neural Autoregressive Topic Model

no code implementations NeurIPS 2012 Hugo Larochelle, Stanislas Lauly

We describe a new model for learning meaningful representations of text documents from an unlabeled collection of documents.

Representation Learning

Practical Bayesian Optimization of Machine Learning Algorithms

4 code implementations NeurIPS 2012 Jasper Snoek, Hugo Larochelle, Ryan P. Adams

In this work, we consider the automatic tuning problem within the framework of Bayesian optimization, in which a learning algorithm's generalization performance is modeled as a sample from a Gaussian process (GP).

Hyperparameter Optimization

Learning to combine foveal glimpses with a third-order Boltzmann machine

no code implementations NeurIPS 2010 Hugo Larochelle, Geoffrey E. Hinton

We describe a model based on a Boltzmann machine with third-order connections that can learn how to accumulate information about a shape over several fixations.

General Classification Image Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.