Search Results for author: Sherjil Ozair

Found 19 papers, 9 papers with code

Procedural Generalization by Planning with Self-Supervised World Models

no code implementations ICLR 2022 Ankesh Anand, Jacob Walker, Yazhe Li, Eszter Vértes, Julian Schrittwieser, Sherjil Ozair, Théophane Weber, Jessica B. Hamrick

One of the key promises of model-based reinforcement learning is the ability to generalize using an internal model of the world to make predictions in novel environments and tasks.

 Ranked #1 on Meta-Learning on ML10 (Meta-test success rate (zero-shot) metric)

Meta-Learning Model-based Reinforcement Learning +1

Pretrained Encoders are All You Need

1 code implementation ICML Workshop URL 2021 Mina Khan, P Srivatsa, Advait Rane, Shriram Chenniappa, Rishabh Anand, Sherjil Ozair, Pattie Maes

Data-efficiency and generalization are key challenges in deep learning and deep reinforcement learning as many models are trained on large-scale, domain-specific, and expensive-to-label datasets.

Contrastive Learning reinforcement-learning +1

Vector Quantized Models for Planning

no code implementations8 Jun 2021 Sherjil Ozair, Yazhe Li, Ali Razavi, Ioannis Antonoglou, Aäron van den Oord, Oriol Vinyals

Our key insight is to use discrete autoencoders to capture the multiple possible effects of an action in a stochastic environment.

SketchTransfer: A Challenging New Task for Exploring Detail-Invariance and the Abstractions Learned by Deep Networks

1 code implementation25 Dec 2019 Alex Lamb, Sherjil Ozair, Vikas Verma, David Ha

In this work we focus on their ability to have invariance towards the presence or absence of details.

Unsupervised State Representation Learning in Atari

3 code implementations NeurIPS 2019 Ankesh Anand, Evan Racah, Sherjil Ozair, Yoshua Bengio, Marc-Alexandre Côté, R. Devon Hjelm

State representation learning, or the ability to capture latent generative factors of an environment, is crucial for building intelligent agents that can perform a wide variety of tasks.

Atari Games Representation Learning

The Journey is the Reward: Unsupervised Learning of Influential Trajectories

no code implementations22 May 2019 Jonathan Binas, Sherjil Ozair, Yoshua Bengio

Unsupervised exploration and representation learning become increasingly important when learning in diverse and sparse environments.

Representation Learning

On Variational Bounds of Mutual Information

3 code implementations16 May 2019 Ben Poole, Sherjil Ozair, Aaron van den Oord, Alexander A. Alemi, George Tucker

Estimating and optimizing Mutual Information (MI) is core to many problems in machine learning; however, bounding MI in high dimensions is challenging.

Representation Learning

Wasserstein Dependency Measure for Representation Learning

no code implementations NeurIPS 2019 Sherjil Ozair, Corey Lynch, Yoshua Bengio, Aaron van den Oord, Sergey Levine, Pierre Sermanet

Mutual information maximization has emerged as a powerful learning objective for unsupervised representation learning obtaining state-of-the-art performance in applications such as object recognition, speech recognition, and reinforcement learning.

Object Recognition reinforcement-learning +3

Maximum Entropy Generators for Energy-Based Models

2 code implementations24 Jan 2019 Rithesh Kumar, Sherjil Ozair, Anirudh Goyal, Aaron Courville, Yoshua Bengio

Maximum likelihood estimation of energy-based models is a challenging problem due to the intractability of the log-likelihood gradient.

Anomaly Detection

Mutual Information Neural Estimation

no code implementations ICML 2018 Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeshwar, Sherjil Ozair, Yoshua Bengio, Aaron Courville, Devon Hjelm

We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks.

General Classification

MINE: Mutual Information Neural Estimation

18 code implementations12 Jan 2018 Mohamed Ishmael Belghazi, Aristide Baratin, Sai Rajeswar, Sherjil Ozair, Yoshua Bengio, Aaron Courville, R. Devon Hjelm

We argue that the estimation of mutual information between high dimensional continuous random variables can be achieved by gradient descent over neural networks.

General Classification

Learning Generative Models with Locally Disentangled Latent Factors

no code implementations ICLR 2018 Brady Neal, Alex Lamb, Sherjil Ozair, Devon Hjelm, Aaron Courville, Yoshua Bengio, Ioannis Mitliagkas

One of the most successful techniques in generative models has been decomposing a complicated generation task into a series of simpler generation tasks.

Generative Adversarial Nets

1 code implementation NeurIPS 2014 Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio

We propose a new framework for estimating generative models via adversarial nets, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake.

Deep Directed Generative Autoencoders

no code implementations2 Oct 2014 Sherjil Ozair, Yoshua Bengio

The objective is to learn an encoder $f(\cdot)$ that maps $X$ to $f(X)$ that has a much simpler distribution than $X$ itself, estimated by $P(H)$.

On the Equivalence Between Deep NADE and Generative Stochastic Networks

no code implementations2 Sep 2014 Li Yao, Sherjil Ozair, Kyunghyun Cho, Yoshua Bengio

Orderless NADEs are trained based on a criterion that stochastically maximizes $P(\mathbf{x})$ with all possible orders of factorizations.

Generative Adversarial Networks

175 code implementations Proceedings of the 27th International Conference on Neural Information Processing Systems 2014 Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio

We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G. The training procedure for G is to maximize the probability of D making a mistake.

Super-Resolution Time-Series Few-Shot Learning with Heterogeneous Channels

Multimodal Transitions for Generative Stochastic Networks

no code implementations19 Dec 2013 Sherjil Ozair, Li Yao, Yoshua Bengio

Generative Stochastic Networks (GSNs) have been recently introduced as an alternative to traditional probabilistic modeling: instead of parametrizing the data distribution directly, one parametrizes a transition operator for a Markov chain whose stationary distribution is an estimator of the data generating distribution.

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