Pascal Poupart
Title: Think Fast -- Resource Constrained Reasoning and Planning under Uncertainty

    Abstract: Recent advances in planning techniques have focused on online search techniques. While these techniques allow practitioners to obtain policies for fairly large problems, they assume that a non-negligible amount of computation can be done between each decision point. In contrast, the recent proliferation of mobile and embedded devices has lead to a surge of applications that could benefit from state of the art planning techniques if they can operate under severe constraints on computational resources. For instance, consider the emerging class of monitoring and assistive applications that run on smart-phones, wearable systems or other mobile devices.  While computational resources are rapidly increasing, energy consumption remains an important bottleneck due to limited battery life. In this talk, I will present some experiments about battery consumption for various types of planning policies on smart-phones. I will then present recent results for the optimization and compilation of policies into controllers with negligible energy consumption during their execution. I will also present recent advances in multi-objective optimization to tradeoff the utility and energy costs resulting from different actions.

    Pascal Poupart is an Associate Professor in the David R. Cheriton School of Computer Science at the University of Waterloo, Waterloo (Canada).  He received the B.Sc. in Mathematics and Computer Science at McGill University, Montreal (Canada) in 1998, the M.Sc. in Computer Science at the University of British Columbia, Vancouver (Canada) in 2000 and the Ph.D. in Computer Science at the University of Toronto, Toronto (Canada) in 2005.  His research focuses on the development of algorithms for reasoning under uncertainty and machine learning with application to Assistive Technologies and Natural Language Processing.  He is most well-known for his contributions to the development of approximate scalable algorithms for partially observable Markov decision processes (POMDPs) and their applications in real-world problems, including automated prompting for people with dementia for the task of handwashing and spoken dialog management. Other notable projects that his research team are currently working on include chatbots for automated personalized conversations and a software platform for health monitoring using wearable sensors. He received a David R. Cheriton Fellowship by the University of Waterloo in 2015 and the Early Researcher Award by the Ontario Ministry of Research and Innovation in 2008.  He was also a co-recipient of the Best Paper Award Runner Up at the 2008 Conference on Uncertainty in Artificial Intelligence (UAI) and the IAPR Best Paper Award at the 2007 International Conference on Computer Vision Systems (ICVS).  He served on the editorial board of the Journal of Artificial Intelligence Research (JAIR) (2008 - 2011) and the Journal of Machine Learning Research (JMLR) (2009 - present).  His research collaborators include Google, Intel, Huawei, Kik Interactive, In the Chat, Slyce.it, the Alzheimer Association, the UW-Schlegel Research Institute for Aging, Sunnybrook Health Science Centre, the Toronto Rehabilitation Institute and the Intelligent Assistive Technology and Systems Laboratory at the University of Toronto.