Sarath Chandar
Appointment
Canada CIFAR AI Chair
Solution Network Member
Integrated AI for Health Imaging
Pan-Canadian AI Strategy
About
Appointed Canada CIFAR AI Chair – 2020
Renewed Canada CIFAR AI Chair – 2025
Sarath Chandar is a Canada CIFAR AI Chair at Mila. He is an assistant professor at the Department of Computer Science and Software Engineering at École Polytechnique de Montréal, an adjunct professor at the Department of Computer Science and Operations Research (DIRO) at Université de Montréal, and an adjunct professor at the Indian Institute of Technology Madras.
Chandar’s research focuses on natural language understanding and in designing machines that can understand human language. He builds lifelong learning systems, which enable machines to learn beyond the initial data gathered in the algorithm they’re deployed in. His research has huge implications for any deployed machine learning systems, including digital personal-assistants, self-driving cars, and even medical applications, such as those that can detect cancer from medical imaging.
Awards
- Canada Research Chair in Lifelong Machine Learning (2023)
- IBM PhD Fellowship (2018)
- Member of Mila dialogue team that won 2nd prize, demonstration track, Neural Information and Processing Systems (2017)
Relevant Publications
De Vries, H., Strub, F., Chandar, S., Pietquin, O., Larochelle, H., & Courville, A. (2017). Guesswhat?! visual object discovery through multi-modal dialogue. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5503-5512).
Serban, I. V., Sankar, C., Germain, M., Zhang, S., Lin, Z., Subramanian, S., … & Bengio, Y. (2017). A deep reinforcement learning chatbot.
Chandar, S., Khapra, M. M., Larochelle, H., & Ravindran, B. (2016). Correlational neural networks. Neural computation, 28(2), 257-285.
Serban, I. V., García-Durán, A., Gulcehre, C., Ahn, S., Chandar, S., Courville, A., & Bengio, Y. (2016). Generating factoid questions with recurrent neural networks: The 30m factoid question-answer corpus.
Lauly, S., Larochelle, H., Khapra, M. M., Ravindran, B., Raykar, V., & Saha, A. (2014). An autoencoder approach to learning bilingual word representations.