Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Anirudh Goyal

Anirudh Goyal

Neural Production Systems


Mar 02, 2021
Anirudh Goyal, Aniket Didolkar, Nan Rosemary Ke, Charles Blundell, Philippe Beaudoin, Nicolas Heess, Michael Mozer, Yoshua Bengio

Figure 1 for Neural Production Systems
Figure 2 for Neural Production Systems
Figure 3 for Neural Production Systems
Figure 4 for Neural Production Systems

  Access Paper or Ask Questions

Coordination Among Neural Modules Through a Shared Global Workspace


Mar 01, 2021
Anirudh Goyal, Aniket Didolkar, Alex Lamb, Kartikeya Badola, Nan Rosemary Ke, Nasim Rahaman, Jonathan Binas, Charles Blundell, Michael Mozer, Yoshua Bengio

Figure 1 for Coordination Among Neural Modules Through a Shared Global Workspace
Figure 2 for Coordination Among Neural Modules Through a Shared Global Workspace
Figure 3 for Coordination Among Neural Modules Through a Shared Global Workspace
Figure 4 for Coordination Among Neural Modules Through a Shared Global Workspace

  Access Paper or Ask Questions

Transformers with Competitive Ensembles of Independent Mechanisms


Feb 27, 2021
Alex Lamb, Di He, Anirudh Goyal, Guolin Ke, Chien-Feng Liao, Mirco Ravanelli, Yoshua Bengio

Figure 1 for Transformers with Competitive Ensembles of Independent Mechanisms
Figure 2 for Transformers with Competitive Ensembles of Independent Mechanisms
Figure 3 for Transformers with Competitive Ensembles of Independent Mechanisms
Figure 4 for Transformers with Competitive Ensembles of Independent Mechanisms
* Under Review, ICML 2021 
  Access Paper or Ask Questions

Towards Causal Representation Learning


Feb 22, 2021
Bernhard Schölkopf, Francesco Locatello, Stefan Bauer, Nan Rosemary Ke, Nal Kalchbrenner, Anirudh Goyal, Yoshua Bengio

Figure 1 for Towards Causal Representation Learning
Figure 2 for Towards Causal Representation Learning
Figure 3 for Towards Causal Representation Learning
Figure 4 for Towards Causal Representation Learning
* Special Issue of Proceedings of the IEEE - Advances in Machine Learning and Deep Neural Networks 
  Access Paper or Ask Questions

Inductive Biases for Deep Learning of Higher-Level Cognition


Dec 07, 2020
Anirudh Goyal, Yoshua Bengio

Figure 1 for Inductive Biases for Deep Learning of Higher-Level Cognition
* This document contains a review of authors research as part of the requirement of AG's predoctoral exam, an overview of the main contributions of the authors few recent papers (co-authored with several other co-authors) as well as a vision of proposed future research 
  Access Paper or Ask Questions

Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers


Oct 15, 2020
Alex Lamb, Anirudh Goyal, Agnieszka Słowik, Michael Mozer, Philippe Beaudoin, Yoshua Bengio

Figure 1 for Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers
Figure 2 for Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers
Figure 3 for Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers
Figure 4 for Neural Function Modules with Sparse Arguments: A Dynamic Approach to Integrating Information across Layers

  Access Paper or Ask Questions

CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning


Oct 08, 2020
Ossama Ahmed, Frederik Träuble, Anirudh Goyal, Alexander Neitz, Manuel Wüthrich, Yoshua Bengio, Bernhard Schölkopf, Stefan Bauer

Figure 1 for CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
Figure 2 for CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
Figure 3 for CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
Figure 4 for CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning
* The first two authors contributed equally 
  Access Paper or Ask Questions

S2RMs: Spatially Structured Recurrent Modules


Jul 13, 2020
Nasim Rahaman, Anirudh Goyal, Muhammad Waleed Gondal, Manuel Wuthrich, Stefan Bauer, Yash Sharma, Yoshua Bengio, Bernhard Schölkopf

Figure 1 for S2RMs: Spatially Structured Recurrent Modules
Figure 2 for S2RMs: Spatially Structured Recurrent Modules
Figure 3 for S2RMs: Spatially Structured Recurrent Modules
Figure 4 for S2RMs: Spatially Structured Recurrent Modules

  Access Paper or Ask Questions

Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems


Jun 30, 2020
Anirudh Goyal, Alex Lamb, Phanideep Gampa, Philippe Beaudoin, Sergey Levine, Charles Blundell, Yoshua Bengio, Michael Mozer

Figure 1 for Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
Figure 2 for Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
Figure 3 for Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
Figure 4 for Object Files and Schemata: Factorizing Declarative and Procedural Knowledge in Dynamical Systems
* Under Review, NeurIPS 2020 
  Access Paper or Ask Questions

Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules


Jun 30, 2020
Sarthak Mittal, Alex Lamb, Anirudh Goyal, Vikram Voleti, Murray Shanahan, Guillaume Lajoie, Michael Mozer, Yoshua Bengio

Figure 1 for Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules
Figure 2 for Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules
Figure 3 for Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules
Figure 4 for Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules
* ICML 2020 
  Access Paper or Ask Questions

Maximum Entropy Models for Fast Adaptation


Jun 30, 2020
Samarth Sinha, Anirudh Goyal, Animesh Garg

Figure 1 for Maximum Entropy Models for Fast Adaptation
Figure 2 for Maximum Entropy Models for Fast Adaptation
Figure 3 for Maximum Entropy Models for Fast Adaptation
Figure 4 for Maximum Entropy Models for Fast Adaptation

  Access Paper or Ask Questions

Untangling tradeoffs between recurrence and self-attention in neural networks


Jun 16, 2020
Giancarlo Kerg, Bhargav Kanuparthi, Anirudh Goyal, Kyle Goyette, Yoshua Bengio, Guillaume Lajoie

Figure 1 for Untangling tradeoffs between recurrence and self-attention in neural networks
Figure 2 for Untangling tradeoffs between recurrence and self-attention in neural networks
Figure 3 for Untangling tradeoffs between recurrence and self-attention in neural networks
Figure 4 for Untangling tradeoffs between recurrence and self-attention in neural networks

  Access Paper or Ask Questions

Is Independence all you need? On the Generalization of Representations Learned from Correlated Data


Jun 14, 2020
Frederik Träuble, Elliot Creager, Niki Kilbertus, Anirudh Goyal, Francesco Locatello, Bernhard Schölkopf, Stefan Bauer

Figure 1 for Is Independence all you need? On the Generalization of Representations Learned from Correlated Data
Figure 2 for Is Independence all you need? On the Generalization of Representations Learned from Correlated Data
Figure 3 for Is Independence all you need? On the Generalization of Representations Learned from Correlated Data
Figure 4 for Is Independence all you need? On the Generalization of Representations Learned from Correlated Data
* 33 pages, 33 figures 
  Access Paper or Ask Questions

The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget


Apr 24, 2020
Anirudh Goyal, Yoshua Bengio, Matthew Botvinick, Sergey Levine

Figure 1 for The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget
Figure 2 for The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget
Figure 3 for The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget
Figure 4 for The Variational Bandwidth Bottleneck: Stochastic Evaluation on an Information Budget
* Published as a conference paper at ICLR 2020 
  Access Paper or Ask Questions

DIBS: Diversity inducing Information Bottleneck in Model Ensembles


Mar 10, 2020
Samarth Sinha, Homanga Bharadhwaj, Anirudh Goyal, Hugo Larochelle, Animesh Garg, Florian Shkurti

Figure 1 for DIBS: Diversity inducing Information Bottleneck in Model Ensembles
Figure 2 for DIBS: Diversity inducing Information Bottleneck in Model Ensembles
Figure 3 for DIBS: Diversity inducing Information Bottleneck in Model Ensembles
Figure 4 for DIBS: Diversity inducing Information Bottleneck in Model Ensembles
* Samarth Sinha* and Homanga Bharadhwaj* contributed equally to this work. Code will be released at https://github.com/rvl-lab-utoronto/dibs 
  Access Paper or Ask Questions

Top-K Training of GANs: Improving Generators by Making Critics Less Critical


Feb 14, 2020
Samarth Sinha, Anirudh Goyal, Colin Raffel, Augustus Odena

Figure 1 for Top-K Training of GANs: Improving Generators by Making Critics Less Critical
Figure 2 for Top-K Training of GANs: Improving Generators by Making Critics Less Critical
Figure 3 for Top-K Training of GANs: Improving Generators by Making Critics Less Critical
Figure 4 for Top-K Training of GANs: Improving Generators by Making Critics Less Critical

  Access Paper or Ask Questions

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


Oct 29, 2019
Samarth Sinha, Han Zhang, Anirudh Goyal, Yoshua Bengio, Hugo Larochelle, Augustus Odena

Figure 1 for Small-GAN: Speeding Up GAN Training Using Core-sets
Figure 2 for Small-GAN: Speeding Up GAN Training Using Core-sets
Figure 3 for Small-GAN: Speeding Up GAN Training Using Core-sets
Figure 4 for Small-GAN: Speeding Up GAN Training Using Core-sets

  Access Paper or Ask Questions

Learning Neural Causal Models from Unknown Interventions


Oct 02, 2019
Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Hugo Larochelle, Chris Pal, Yoshua Bengio

Figure 1 for Learning Neural Causal Models from Unknown Interventions
Figure 2 for Learning Neural Causal Models from Unknown Interventions
Figure 3 for Learning Neural Causal Models from Unknown Interventions
Figure 4 for Learning Neural Causal Models from Unknown Interventions

  Access Paper or Ask Questions

Recurrent Independent Mechanisms


Sep 26, 2019
Anirudh Goyal, Alex Lamb, Jordan Hoffmann, Shagun Sodhani, Sergey Levine, Yoshua Bengio, Bernhard Schölkopf

Figure 1 for Recurrent Independent Mechanisms
Figure 2 for Recurrent Independent Mechanisms
Figure 3 for Recurrent Independent Mechanisms
Figure 4 for Recurrent Independent Mechanisms

  Access Paper or Ask Questions

Learning the Arrow of Time


Jul 02, 2019
Nasim Rahaman, Steffen Wolf, Anirudh Goyal, Roman Remme, Yoshua Bengio

Figure 1 for Learning the Arrow of Time
Figure 2 for Learning the Arrow of Time
Figure 3 for Learning the Arrow of Time
Figure 4 for Learning the Arrow of Time
* A shorter version of this work was presented at the Theoretical Phyiscs for Deep Learning Workshop, ICML 2019 
  Access Paper or Ask Questions

Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives


Jun 25, 2019
Anirudh Goyal, Shagun Sodhani, Jonathan Binas, Xue Bin Peng, Sergey Levine, Yoshua Bengio

Figure 1 for Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
Figure 2 for Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
Figure 3 for Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
Figure 4 for Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives
* Preprint, Under Review 
  Access Paper or Ask Questions

Learning Powerful Policies by Using Consistent Dynamics Model


Jun 11, 2019
Shagun Sodhani, Anirudh Goyal, Tristan Deleu, Yoshua Bengio, Sergey Levine, Jian Tang

Figure 1 for Learning Powerful Policies by Using Consistent Dynamics Model
Figure 2 for Learning Powerful Policies by Using Consistent Dynamics Model
Figure 3 for Learning Powerful Policies by Using Consistent Dynamics Model
Figure 4 for Learning Powerful Policies by Using Consistent Dynamics Model
* Accpted at RLDM 2019 
  Access Paper or Ask Questions

State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations


May 26, 2019
Alex Lamb, Jonathan Binas, Anirudh Goyal, Sandeep Subramanian, Ioannis Mitliagkas, Denis Kazakov, Yoshua Bengio, Michael C. Mozer

Figure 1 for State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
Figure 2 for State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
Figure 3 for State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
Figure 4 for State-Reification Networks: Improving Generalization by Modeling the Distribution of Hidden Representations
* ICML 2019 [full oral]. arXiv admin note: text overlap with arXiv:1805.08394 
  Access Paper or Ask Questions

InfoBot: Transfer and Exploration via the Information Bottleneck


Apr 04, 2019
Anirudh Goyal, Riashat Islam, Daniel Strouse, Zafarali Ahmed, Matthew Botvinick, Hugo Larochelle, Yoshua Bengio, Sergey Levine

Figure 1 for InfoBot: Transfer and Exploration via the Information Bottleneck
Figure 2 for InfoBot: Transfer and Exploration via the Information Bottleneck
Figure 3 for InfoBot: Transfer and Exploration via the Information Bottleneck
Figure 4 for InfoBot: Transfer and Exploration via the Information Bottleneck
* Accepted at ICLR'19 
  Access Paper or Ask Questions

Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future


Mar 16, 2019
Nan Rosemary Ke, Amanpreet Singh, Ahmed Touati, Anirudh Goyal, Yoshua Bengio, Devi Parikh, Dhruv Batra

Figure 1 for Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future
Figure 2 for Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future
Figure 3 for Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future
Figure 4 for Learning Dynamics Model in Reinforcement Learning by Incorporating the Long Term Future
* To appear at ICLR 2019 
  Access Paper or Ask Questions

Communication Topologies Between Learning Agents in Deep Reinforcement Learning


Feb 16, 2019
Dhaval Adjodah, Dan Calacci, Abhimanyu Dubey, Anirudh Goyal, Peter Krafft, Esteban Moro, Alex Pentland

Figure 1 for Communication Topologies Between Learning Agents in Deep Reinforcement Learning
Figure 2 for Communication Topologies Between Learning Agents in Deep Reinforcement Learning
Figure 3 for Communication Topologies Between Learning Agents in Deep Reinforcement Learning
Figure 4 for Communication Topologies Between Learning Agents in Deep Reinforcement Learning
* arXiv admin note: substantial text overlap with arXiv:1811.12556 
  Access Paper or Ask Questions

A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms


Feb 04, 2019
Yoshua Bengio, Tristan Deleu, Nasim Rahaman, Rosemary Ke, Sébastien Lachapelle, Olexa Bilaniuk, Anirudh Goyal, Christopher Pal

Figure 1 for A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
Figure 2 for A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
Figure 3 for A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms
Figure 4 for A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms

  Access Paper or Ask Questions