Aaron Courville

is this you? claim profile

∙ 0 followers
Université de Montréal

Assistant Professor at University of Montreal

Out-of-Distribution Generalization via Risk Extrapolation (REx)

Generalizing outside of the training distribution is an open challenge f...
03/02/2020 ∙ by David Krueger, et al. ∙ 25 ∙ share

read it
Selective Brain Damage: Measuring the Disparate Impact of Model Pruning

Neural network pruning techniques have demonstrated it is possible to re...
11/13/2019 ∙ by Sara Hooker, et al. ∙ 20 ∙ share

read it
Icentia11K: An Unsupervised Representation Learning Dataset for Arrhythmia Subtype Discovery

We release the largest public ECG dataset of continuous raw signals for ...
10/21/2019 ∙ by Shawn Tan, et al. ∙ 12 ∙ share

read it
AR-DAE: Towards Unbiased Neural Entropy Gradient Estimation

Entropy is ubiquitous in machine learning, but it is in general intracta...
06/09/2020 ∙ by Jae Hyun Lim, et al. ∙ 12 ∙ share

read it
Improved Conditional VRNNs for Video Prediction

Predicting future frames for a video sequence is a challenging generativ...
04/27/2019 ∙ by Lluis Castrejon, et al. ∙ 8 ∙ share

read it
Learning Distributed Representations from Reviews for Collaborative Filtering

Recent work has shown that collaborative filter-based recommender system...
06/18/2018 ∙ by Amjad Almahairi, et al. ∙ 6 ∙ share

read it
Blindfold Baselines for Embodied QA

We explore blindfold (question-only) baselines for Embodied Question Ans...
11/12/2018 ∙ by Ankesh Anand, et al. ∙ 6 ∙ share

read it
Systematic Generalization: What Is Required and Can It Be Learned?

Numerous models for grounded language understanding have been recently p...
11/30/2018 ∙ by Dzmitry Bahdanau, et al. ∙ 6 ∙ share

read it
Detecting semantic anomalies

We critically appraise the recent interest in out-of-distribution (OOD) ...
08/13/2019 ∙ by Faruk Ahmed, et al. ∙ 5 ∙ share

read it
CLOSURE: Assessing Systematic Generalization of CLEVR Models

The CLEVR dataset of natural-looking questions about 3D-rendered scenes ...
12/12/2019 ∙ by Dzmitry Bahdanau, et al. ∙ 5 ∙ share

read it
No Press Diplomacy: Modeling Multi-Agent Gameplay

Diplomacy is a seven-player non-stochastic, non-cooperative game, where ...
09/04/2019 ∙ by Philip Paquette, et al. ∙ 4 ∙ share

read it
Straight to the Tree: Constituency Parsing with Neural Syntactic Distance

In this work, we propose a novel constituency parsing scheme. The model ...
06/11/2018 ∙ by Yikang Shen, et al. ∙ 2 ∙ share

read it
Approximate Exploration through State Abstraction

Although exploration in reinforcement learning is well understood from a...
08/29/2018 ∙ by Adrien Ali Taïga, et al. ∙ 2 ∙ share

read it
Maximum Entropy Generators for Energy-Based Models

Unsupervised learning is about capturing dependencies between variables ...
01/24/2019 ∙ by Rithesh Kumar, et al. ∙ 2 ∙ share

read it
Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment

This paper provides an empirical evaluation of recently developed explor...
08/06/2019 ∙ by Adrien Ali Taïga, et al. ∙ 2 ∙ share

read it
Deep Generative Modeling of LiDAR Data

Building models capable of generating structured output is a key challen...
12/04/2018 ∙ by Lucas Caccia, et al. ∙ 1 ∙ share

read it
VideoNavQA: Bridging the Gap between Visual and Embodied Question Answering

Embodied Question Answering (EQA) is a recently proposed task, where an ...
08/14/2019 ∙ by Cătălina Cangea, et al. ∙ 1 ∙ share

read it
Countering Language Drift with Seeded Iterated Learning

Supervised learning methods excel at capturing statistical properties of...
03/28/2020 ∙ by Yuchen Lu, et al. ∙ 1 ∙ share

read it
A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM

We present Korbit, a large-scale, open-domain, mixed-interface, dialogue...
05/06/2020 ∙ by Iulian Vlad Serban, et al. ∙ 1 ∙ share

read it
Representation Learning: A Review and New Perspectives

The success of machine learning algorithms generally depends on data rep...
06/24/2012 ∙ by Yoshua Bengio, et al. ∙ 0 ∙ share

read it
Generative Adversarial Networks

We propose a new framework for estimating generative models via an adver...
06/10/2014 ∙ by Ian J. Goodfellow, et al. ∙ 0 ∙ share

read it
Bayesian Hypernetworks

We propose Bayesian hypernetworks: a framework for approximate Bayesian ...
10/13/2017 ∙ by David Krueger, et al. ∙ 0 ∙ share

read it
Learnable Explicit Density for Continuous Latent Space and Variational Inference

In this paper, we study two aspects of the variational autoencoder (VAE)...
10/06/2017 ∙ by Chin-Wei Huang, et al. ∙ 0 ∙ share

read it
FiLM: Visual Reasoning with a General Conditioning Layer

We introduce a general-purpose conditioning method for neural networks c...
09/22/2017 ∙ by Ethan Perez, et al. ∙ 0 ∙ share

read it
Dynamic Capacity Networks

We introduce the Dynamic Capacity Network (DCN), a neural network that c...
11/24/2015 ∙ by Amjad Almahairi, et al. ∙ 0 ∙ share

read it
Delving Deeper into Convolutional Networks for Learning Video Representations

We propose an approach to learn spatio-temporal features in videos from ...
11/19/2015 ∙ by Nicolas Ballas, et al. ∙ 0 ∙ share

read it
A Closer Look at Memorization in Deep Networks

We examine the role of memorization in deep learning, drawing connection...
06/16/2017 ∙ by Devansh Arpit, et al. ∙ 0 ∙ share

read it
SampleRNN: An Unconditional End-to-End Neural Audio Generation Model

In this paper we propose a novel model for unconditional audio generatio...
12/22/2016 ∙ by Soroush Mehri, et al. ∙ 0 ∙ share

read it
Learning Visual Reasoning Without Strong Priors

Achieving artificial visual reasoning - the ability to answer image-rela...
07/10/2017 ∙ by Ethan Perez, et al. ∙ 0 ∙ share

read it
Modulating early visual processing by language

It is commonly assumed that language refers to high-level visual concept...
07/02/2017 ∙ by Harm de Vries, et al. ∙ 0 ∙ share

read it
Improved Training of Wasserstein GANs

Generative Adversarial Networks (GANs) are powerful generative models, b...
03/31/2017 ∙ by Ishaan Gulrajani, et al. ∙ 0 ∙ share

read it
Professor Forcing: A New Algorithm for Training Recurrent Networks

The Teacher Forcing algorithm trains recurrent networks by supplying obs...
10/27/2016 ∙ by Alex Lamb, et al. ∙ 0 ∙ share

read it
Brain Tumor Segmentation with Deep Neural Networks

In this paper, we present a fully automatic brain tumor segmentation met...
05/13/2015 ∙ by Mohammad Havaei, et al. ∙ 0 ∙ share

read it
Adversarially Learned Inference

We introduce the adversarially learned inference (ALI) model, which join...
06/02/2016 ∙ by Vincent Dumoulin, et al. ∙ 0 ∙ share

read it
Generalizable Features From Unsupervised Learning

Humans learn a predictive model of the world and use this model to reaso...
12/12/2016 ∙ by Mehdi Mirza, et al. ∙ 0 ∙ share

read it
A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images

Colorectal cancer (CRC) is the third cause of cancer death worldwide. Cu...
12/02/2016 ∙ by David Vazquez, et al. ∙ 0 ∙ share

read it
GuessWhat?! Visual object discovery through multi-modal dialogue

We introduce GuessWhat?!, a two-player guessing game as a testbed for re...
11/23/2016 ∙ by Harm de Vries, et al. ∙ 0 ∙ share

read it
A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering

While deep convolutional neural networks frequently approach or exceed h...
11/23/2016 ∙ by Tegan Maharaj, et al. ∙ 0 ∙ share

read it
Discriminative Regularization for Generative Models

We explore the question of whether the representations learned by classi...
02/09/2016 ∙ by Alex Lamb, et al. ∙ 0 ∙ share

read it
Variance Reduction in SGD by Distributed Importance Sampling

Humans are able to accelerate their learning by selecting training mater...
11/20/2015 ∙ by Guillaume Alain, et al. ∙ 0 ∙ share

read it
Deep Tempering

Restricted Boltzmann Machines (RBMs) are one of the fundamental building...
10/01/2014 ∙ by Guillaume Desjardins, et al. ∙ 0 ∙ share

read it
On Training Deep Boltzmann Machines

The deep Boltzmann machine (DBM) has been an important development in th...
03/20/2012 ∙ by Guillaume Desjardins, et al. ∙ 0 ∙ share

read it
An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networks

Catastrophic forgetting is a problem faced by many machine learning mode...
12/21/2013 ∙ by Ian J. Goodfellow, et al. ∙ 0 ∙ share

read it
An empirical analysis of dropout in piecewise linear networks

The recently introduced dropout training criterion for neural networks h...
12/21/2013 ∙ by David Warde-Farley, et al. ∙ 0 ∙ share

read it
On the Challenges of Physical Implementations of RBMs

Restricted Boltzmann machines (RBMs) are powerful machine learning model...
12/18/2013 ∙ by Vincent Dumoulin, et al. ∙ 0 ∙ share

read it
Challenges in Representation Learning: A report on three machine learning contests

The ICML 2013 Workshop on Challenges in Representation Learning focused ...
07/01/2013 ∙ by Ian J. Goodfellow, et al. ∙ 0 ∙ share

read it
Maxout Networks

We consider the problem of designing models to leverage a recently intro...
02/18/2013 ∙ by Ian J. Goodfellow, et al. ∙ 0 ∙ share

read it
ReNet: A Recurrent Neural Network Based Alternative to Convolutional Networks

In this paper, we propose a deep neural network architecture for object ...
05/03/2015 ∙ by Francesco Visin, et al. ∙ 0 ∙ share

read it
Joint Training Deep Boltzmann Machines for Classification

We introduce a new method for training deep Boltzmann machines jointly. ...
01/16/2013 ∙ by Ian J. Goodfellow, et al. ∙ 0 ∙ share

read it
Metric-Free Natural Gradient for Joint-Training of Boltzmann Machines

This paper introduces the Metric-Free Natural Gradient (MFNG) algorithm ...
01/16/2013 ∙ by Guillaume Desjardins, et al. ∙ 0 ∙ share

read it

Aaron Courville

Featured Co-authors