Pascal Poupart
Appointment
Canada CIFAR AI Chair
Pan-Canadian AI Strategy
About
Appointed Canada CIFAR AI Chair – 2018
Pascal Poupart is a Canada CIFAR AI Chair at the Vector Institute, and a professor in the David R. Cheriton School of Computer Science at the University of Waterloo.
Poupart’s research focuses on machine learning and decision-theoretic planning with application to natural language processing, sports analytics, telecommunication networks and assistive technologies. He is most well-known for his contributions to algorithms for decision processes and their applications in real-world problems, including helping people with dementia in activities of daily living and automated dialog systems. Poupart is also leading research on chatbots, video analysis of hockey games and data driven management of telecommunication networks.
Awards
- David R. Cheriton Faculty Fellowship, 2015-2018
- Best Student Paper Award Runner-Up, SAT-2017
- Best Main Track Solver and Best Application Solver, SAT-2016 Competition
- Best Paper Award Runner-Up, UAI-2008
- Ontario Early Researcher Award, 2008-2013
Relevant Publications
Hoey, J., Poupart, P., von Bertoldi, A., Craig, T., Boutilier, C., & Mihailidis, A. (2010). Automated handwashing assistance for persons with dementia using video and a partially observable Markov decision process. Computer Vision and Image Understanding, 114(5), 503-519.
Poupart, P., Vlassis, N., Hoey, J., & Regan, K. (2006). An analytic solution to discrete Bayesian reinforcement learning. In Proceedings of the 23rd international conference on Machine learning (pp. 697-704).
Porta, J. M., Vlassis, N., Spaan, M. T., & Poupart, P. (2006). Point-based value iteration for continuous POMDPs.
Poupart, P. (2005). Exploiting structure to efficiently solve large scale partially observable Markov decision processes (pp. 3239-3239). Toronto, Canada: University of Toronto.
Poupart, P., & Boutilier, C. (2003). Bounded finite state controllers. Advances in neural information processing systems, 16, 823-830.