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 Sarath Chandar

Sarath Chandar

Continuous Coordination As a Realistic Scenario for Lifelong Learning


Mar 04, 2021
Hadi Nekoei, Akilesh Badrinaaraayanan, Aaron Courville, Sarath Chandar

Figure 1 for Continuous Coordination As a Realistic Scenario for Lifelong Learning
Figure 2 for Continuous Coordination As a Realistic Scenario for Lifelong Learning
Figure 3 for Continuous Coordination As a Realistic Scenario for Lifelong Learning
Figure 4 for Continuous Coordination As a Realistic Scenario for Lifelong Learning

  Access Paper or Ask Questions

IIRC: Incremental Implicitly-Refined Classification


Jan 11, 2021
Mohamed Abdelsalam, Mojtaba Faramarzi, Shagun Sodhani, Sarath Chandar

Figure 1 for IIRC: Incremental Implicitly-Refined Classification
Figure 2 for IIRC: Incremental Implicitly-Refined Classification
Figure 3 for IIRC: Incremental Implicitly-Refined Classification
Figure 4 for IIRC: Incremental Implicitly-Refined Classification

  Access Paper or Ask Questions

Maximum Reward Formulation In Reinforcement Learning


Oct 08, 2020
Sai Krishna Gottipati, Yashaswi Pathak, Rohan Nuttall, Sahir, Raviteja Chunduru, Ahmed Touati, Sriram Ganapathi Subramanian, Matthew E. Taylor, Sarath Chandar

Figure 1 for Maximum Reward Formulation In Reinforcement Learning
Figure 2 for Maximum Reward Formulation In Reinforcement Learning
Figure 3 for Maximum Reward Formulation In Reinforcement Learning
Figure 4 for Maximum Reward Formulation In Reinforcement Learning
* 13 pages, 5 figures 
  Access Paper or Ask Questions

MLMLM: Link Prediction with Mean Likelihood Masked Language Model


Sep 15, 2020
Louis Clouatre, Philippe Trempe, Amal Zouaq, Sarath Chandar

Figure 1 for MLMLM: Link Prediction with Mean Likelihood Masked Language Model
Figure 2 for MLMLM: Link Prediction with Mean Likelihood Masked Language Model
Figure 3 for MLMLM: Link Prediction with Mean Likelihood Masked Language Model
Figure 4 for MLMLM: Link Prediction with Mean Likelihood Masked Language Model

  Access Paper or Ask Questions

How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics


Aug 24, 2020
Prasanna Parthasarathi, Joelle Pineau, Sarath Chandar

Figure 1 for How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics
Figure 2 for How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics
Figure 3 for How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics
Figure 4 for How To Evaluate Your Dialogue System: Probe Tasks as an Alternative for Token-level Evaluation Metrics

  Access Paper or Ask Questions

Slot Contrastive Networks: A Contrastive Approach for Representing Objects


Jul 18, 2020
Evan Racah, Sarath Chandar

Figure 1 for Slot Contrastive Networks: A Contrastive Approach for Representing Objects
Figure 2 for Slot Contrastive Networks: A Contrastive Approach for Representing Objects
Figure 3 for Slot Contrastive Networks: A Contrastive Approach for Representing Objects
Figure 4 for Slot Contrastive Networks: A Contrastive Approach for Representing Objects
* Presented at ICML 2020 Workshop: Object-Oriented Learning (OOL): Perception, Representation, and Reasoning 
  Access Paper or Ask Questions

The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning


Jul 07, 2020
Harm van Seijen, Hadi Nekoei, Evan Racah, Sarath Chandar

Figure 1 for The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning
Figure 2 for The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning
Figure 3 for The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning
Figure 4 for The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning

  Access Paper or Ask Questions

PatchUp: A Regularization Technique for Convolutional Neural Networks


Jun 14, 2020
Mojtaba Faramarzi, Mohammad Amini, Akilesh Badrinaaraayanan, Vikas Verma, Sarath Chandar

Figure 1 for PatchUp: A Regularization Technique for Convolutional Neural Networks
Figure 2 for PatchUp: A Regularization Technique for Convolutional Neural Networks
Figure 3 for PatchUp: A Regularization Technique for Convolutional Neural Networks
Figure 4 for PatchUp: A Regularization Technique for Convolutional Neural Networks

  Access Paper or Ask Questions

Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning


May 20, 2020
Sai Krishna Gottipati, Boris Sattarov, Sufeng Niu, Yashaswi Pathak, Haoran Wei, Shengchao Liu, Karam M. J. Thomas, Simon Blackburn, Connor W. Coley, Jian Tang, Sarath Chandar, Yoshua Bengio

Figure 1 for Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
Figure 2 for Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
Figure 3 for Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
Figure 4 for Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
* added the statistics of top-100 compounds used logP metric with scaled components added values of the initial reactants to the box plots some values in tables are recalculated due to the inconsistent environments on different machines. corresponding benchmarks were rerun with the requirements on github. no significant changes in the results. corrected figures in the Appendix 
  Access Paper or Ask Questions

Towards Lossless Encoding of Sentences


Jun 04, 2019
Gabriele Prato, Mathieu Duchesneau, Sarath Chandar, Alain Tapp

Figure 1 for Towards Lossless Encoding of Sentences
Figure 2 for Towards Lossless Encoding of Sentences
Figure 3 for Towards Lossless Encoding of Sentences
Figure 4 for Towards Lossless Encoding of Sentences
* Accepted at ACL 2019 
  Access Paper or Ask Questions

Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study


Jun 04, 2019
Chinnadhurai Sankar, Sandeep Subramanian, Christopher Pal, Sarath Chandar, Yoshua Bengio

Figure 1 for Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
Figure 2 for Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
Figure 3 for Do Neural Dialog Systems Use the Conversation History Effectively? An Empirical Study
* To appear at ACL 2019 
  Access Paper or Ask Questions

Structure Learning for Neural Module Networks


May 27, 2019
Vardaan Pahuja, Jie Fu, Sarath Chandar, Christopher J. Pal

Figure 1 for Structure Learning for Neural Module Networks
Figure 2 for Structure Learning for Neural Module Networks
Figure 3 for Structure Learning for Neural Module Networks
Figure 4 for Structure Learning for Neural Module Networks

  Access Paper or Ask Questions

The Hanabi Challenge: A New Frontier for AI Research


Feb 01, 2019
Nolan Bard, Jakob N. Foerster, Sarath Chandar, Neil Burch, Marc Lanctot, H. Francis Song, Emilio Parisotto, Vincent Dumoulin, Subhodeep Moitra, Edward Hughes, Iain Dunning, Shibl Mourad, Hugo Larochelle, Marc G. Bellemare, Michael Bowling

Figure 1 for The Hanabi Challenge: A New Frontier for AI Research
Figure 2 for The Hanabi Challenge: A New Frontier for AI Research
Figure 3 for The Hanabi Challenge: A New Frontier for AI Research
Figure 4 for The Hanabi Challenge: A New Frontier for AI Research
* 37 pages, 5 figures, submitted to Artificial Intelligence 
  Access Paper or Ask Questions

Environments for Lifelong Reinforcement Learning


Dec 06, 2018
Khimya Khetarpal, Shagun Sodhani, Sarath Chandar, Doina Precup

* Accepted at 2nd Continual Learning Workshop, Neural Information Processing Systems (NeurIPS) 2018 
  Access Paper or Ask Questions

On Training Recurrent Neural Networks for Lifelong Learning


Nov 16, 2018
Shagun Sodhani, Sarath Chandar, Yoshua Bengio

Figure 1 for On Training Recurrent Neural Networks for Lifelong Learning
Figure 2 for On Training Recurrent Neural Networks for Lifelong Learning
Figure 3 for On Training Recurrent Neural Networks for Lifelong Learning
Figure 4 for On Training Recurrent Neural Networks for Lifelong Learning
* Accepted at the Continual Learning Workshop , NIPS 2018 
  Access Paper or Ask Questions

Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph


Oct 04, 2018
Amrita Saha, Vardaan Pahuja, Mitesh M. Khapra, Karthik Sankaranarayanan, Sarath Chandar

Figure 1 for Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph
Figure 2 for Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph
Figure 3 for Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph
Figure 4 for Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph
* Accepted in AAAI'18 
  Access Paper or Ask Questions

Language Expansion In Text-Based Games


May 17, 2018
Ghulam Ahmed Ansari, Sagar J P, Sarath Chandar, Balaraman Ravindran

Figure 1 for Language Expansion In Text-Based Games
Figure 2 for Language Expansion In Text-Based Games
Figure 3 for Language Expansion In Text-Based Games
Figure 4 for Language Expansion In Text-Based Games
* 9 pages. arXiv admin note: text overlap with arXiv:1511.06295 by other authors 
  Access Paper or Ask Questions

A Deep Reinforcement Learning Chatbot (Short Version)


Jan 20, 2018
Iulian V. Serban, Chinnadhurai Sankar, Mathieu Germain, Saizheng Zhang, Zhouhan Lin, Sandeep Subramanian, Taesup Kim, Michael Pieper, Sarath Chandar, Nan Rosemary Ke, Sai Rajeswar, Alexandre de Brebisson, Jose M. R. Sotelo, Dendi Suhubdy, Vincent Michalski, Alexandre Nguyen, Joelle Pineau, Yoshua Bengio

Figure 1 for A Deep Reinforcement Learning Chatbot (Short Version)
Figure 2 for A Deep Reinforcement Learning Chatbot (Short Version)
Figure 3 for A Deep Reinforcement Learning Chatbot (Short Version)
* 9 pages, 1 figure, 2 tables; presented at NIPS 2017, Conversational AI: "Today's Practice and Tomorrow's Potential" Workshop 
  Access Paper or Ask Questions

A Deep Reinforcement Learning Chatbot


Nov 05, 2017
Iulian V. Serban, Chinnadhurai Sankar, Mathieu Germain, Saizheng Zhang, Zhouhan Lin, Sandeep Subramanian, Taesup Kim, Michael Pieper, Sarath Chandar, Nan Rosemary Ke, Sai Rajeshwar, Alexandre de Brebisson, Jose M. R. Sotelo, Dendi Suhubdy, Vincent Michalski, Alexandre Nguyen, Joelle Pineau, Yoshua Bengio

Figure 1 for A Deep Reinforcement Learning Chatbot
Figure 2 for A Deep Reinforcement Learning Chatbot
Figure 3 for A Deep Reinforcement Learning Chatbot
Figure 4 for A Deep Reinforcement Learning Chatbot
* 40 pages, 9 figures, 11 tables 
  Access Paper or Ask Questions

Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes


Mar 17, 2017
Caglar Gulcehre, Sarath Chandar, Kyunghyun Cho, Yoshua Bengio

Figure 1 for Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
Figure 2 for Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
Figure 3 for Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
Figure 4 for Dynamic Neural Turing Machine with Soft and Hard Addressing Schemes
* 13 pages, 3 figures 
  Access Paper or Ask Questions

GuessWhat?! Visual object discovery through multi-modal dialogue


Feb 06, 2017
Harm de Vries, Florian Strub, Sarath Chandar, Olivier Pietquin, Hugo Larochelle, Aaron Courville

Figure 1 for GuessWhat?! Visual object discovery through multi-modal dialogue
Figure 2 for GuessWhat?! Visual object discovery through multi-modal dialogue
Figure 3 for GuessWhat?! Visual object discovery through multi-modal dialogue
Figure 4 for GuessWhat?! Visual object discovery through multi-modal dialogue
* 23 pages; CVPR 2017 submission; see https://guesswhat.ai 
  Access Paper or Ask Questions

Memory Augmented Neural Networks with Wormhole Connections


Jan 30, 2017
Caglar Gulcehre, Sarath Chandar, Yoshua Bengio

Figure 1 for Memory Augmented Neural Networks with Wormhole Connections
Figure 2 for Memory Augmented Neural Networks with Wormhole Connections
Figure 3 for Memory Augmented Neural Networks with Wormhole Connections
Figure 4 for Memory Augmented Neural Networks with Wormhole Connections

  Access Paper or Ask Questions

Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning


Jul 01, 2016
Janarthanan Rajendran, Mitesh M. Khapra, Sarath Chandar, Balaraman Ravindran

Figure 1 for Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning
Figure 2 for Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning
Figure 3 for Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning
Figure 4 for Bridge Correlational Neural Networks for Multilingual Multimodal Representation Learning
* Published at NAACL-HLT 2016 
  Access Paper or Ask Questions

A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation


Jun 15, 2016
Amrita Saha, Mitesh M. Khapra, Sarath Chandar, Janarthanan Rajendran, Kyunghyun Cho

Figure 1 for A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation
Figure 2 for A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation
Figure 3 for A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation
Figure 4 for A Correlational Encoder Decoder Architecture for Pivot Based Sequence Generation
* 10 pages 
  Access Paper or Ask Questions

Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus


May 29, 2016
Iulian Vlad Serban, Alberto García-Durán, Caglar Gulcehre, Sungjin Ahn, Sarath Chandar, Aaron Courville, Yoshua Bengio

Figure 1 for Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus
Figure 2 for Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus
Figure 3 for Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus
Figure 4 for Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus
* 13 pages, 1 figure, 7 tables 
  Access Paper or Ask Questions

Hierarchical Memory Networks


May 24, 2016
Sarath Chandar, Sungjin Ahn, Hugo Larochelle, Pascal Vincent, Gerald Tesauro, Yoshua Bengio

Figure 1 for Hierarchical Memory Networks
Figure 2 for Hierarchical Memory Networks
* 10 pages 
  Access Paper or Ask Questions

Clustering is Efficient for Approximate Maximum Inner Product Search


Nov 30, 2015
Alex Auvolat, Sarath Chandar, Pascal Vincent, Hugo Larochelle, Yoshua Bengio

Figure 1 for Clustering is Efficient for Approximate Maximum Inner Product Search
Figure 2 for Clustering is Efficient for Approximate Maximum Inner Product Search
Figure 3 for Clustering is Efficient for Approximate Maximum Inner Product Search
Figure 4 for Clustering is Efficient for Approximate Maximum Inner Product Search
* 10 pages, Under review at ICLR 2016 
  Access Paper or Ask Questions

Correlational Neural Networks


Oct 12, 2015
Sarath Chandar, Mitesh M. Khapra, Hugo Larochelle, Balaraman Ravindran

* 27 pages. To Appear in Neural Computation 
  Access Paper or Ask Questions