I am a fourth year Ph.D. candidate at University of Montreal, advised by Yoshua Bengio and Hugo Larochelle. I am a recepient of the IBM PhD Fellowship for 2018.
Before joining University of Montreal, I was a Research Software Engineer at IBM India Research Lab during August,2014 - May,2015. I obtained my MS by Research at Indian Institute of Technology Madras where I was working with Balaraman Ravindran.
Artificial Intelligence, Machine Learning, Deep Learning, Natural Language Processing, Reinforcement Learning, Lifelong Learning.
Our recent work on Non-saturating Recurrent Units (NRUs) accepted at AAAI 2019. Preprint available here.
Two of our recent works on lifelong learning accepted at NeurIPS continual learning workshop: On training RNNs for lifelong learning (Oral) and Environments for lifelong reinforcement learning (Poster).
Click Here for complete list of publications.
Towards Non-saturating Recurrent Units for Modelling Long-term Dependencies.
Sarath Chandar*, Chinnadhurai Sankar*, Eugene Vorontsov, Samira Ebrahimi Kahou, Yoshua Bengio.
Proceedings of AAAI, 2019.
Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph.
Amrita Saha, Vardaan Pahuja, Mitesh M. Khapra, Karthik Sankaranarayanan, Sarath Chandar.
Proceedings of AAAI, 2018.
Memory Augmented Neural Networks with Wormhole Connections.
Caglar Gulcehre, Sarath Chandar, Yoshua Bengio.
In arXiv, 2017.
Lecturer at McGill University.
Teaching assistant at University of Montreal.
Teaching assistant at IIT Madras.
- Fall 2014 : Introduction to Machine Learning.
- Spring 2014 : Probabilistic Reasoning in AI.
- Fall 2013 : Introduction to Machine Learning.
- Spring 2013 : Languages, Machines and Computation.
- Fall 2012 : Computational Engineering.
- Co-organized 2nd Workshop on Lifelong Learning: A Reinforcement Learning Approach at ICML/IJCAI/AAMAS, in 2018, with Daniel Mankowitz, Tom Zahavy, Balaraman Ravindran, and Shie Mannor.
- Co-organized Lifelong Learning: A Reinforcement Learning Approach workshop at International Conference on Machine Learning (ICML), in 2017, with Balaraman Ravindran, Daniel Mankowitz, Shie Mannor, Tom Zahavy.
- Co-organized Deep Reinforcement Learning: Frontiers and Challenges workshop at International Joint Conference on Artificial Intelligence (IJCAI), in 2016, with Sridhar Mahadevan, Balaraman Ravindran, Gerald Tesauro.
- NeurIPS (2016, 2017, 2018)
- ICLR (2017, 2018, 2019)
- ICML (2018, 2019)
- COLING (2018)
- Neural Computation
- ACM Transactions on Asian and Low-Resource Language Information Processing