Keep up to date on research coming out of the University of Alberta and beyond!
The Artificial Intelligence Seminar is a weekly meeting where researchers interested in AI can share their research. Presenters include both local speakers from the University of Alberta and visitors from other institutions. Topics related in any way to Artificial Intelligence can be presented, from foundational theoretical work to innovative applications of AI techniques to new fields and problems.
Each AI Seminar happens (unless otherwise specified) at 12 – 1 pm at the University of Alberta Computing Science Center, CSC B-10 (click here for a floorplan). Plus, pizza is provided for all attendees!
Here are the AI Seminars happening in February 2019:
Ilbin and Bo
Speaker 1: Ilbin Lee
Title: Introducing some Machine Learning Research Projects in Wildfire and Healthcare Applications
Abstract: In this talk, Ilbin Lee will briefly introduce machine learning projects in wildfire and hospital operations. These two projects involve the use of machine intelligence models to predict risk and therefore increase the likelihood of successful intervention.
Bio: Ilbin Lee is an assistant professor in operations management at the University of Alberta School of Business. He was a postdoctoral fellow in the School of Industrial and Systems Engineering at Georgia Institute of Technology. He obtained his
in Industrial and Operations Engineering at the University of Michigan in 2015. His research interests include sequential decision-making based on data and prediction, computational optimization, and wildfire and healthcare applications. PhD
Speaker 2: Bo Cao
Title: Machine Learning Applied to Psychiatric Disorders Understanding
Abstract: Bo Cao will talk about several studies using machine learning and brain imaging to understand psychiatric disorders, identify patients with these disorders and predict the treatment outcomes.
Bio: Bo Cao is trained in mathematics (BSc), psychology (MSc), computational neuroscience (
PhD), neuroimaging and psychiatry (postdoc), and has a strong passion for understanding the fundamental mechanisms of how the brain works and how to cure the brain when the mechanisms are disturbed. He currently is an Assistant Professor of the Department of Psychiatry at the University of Alberta.
More details to come
February 22: Hengshuai Yao
Title: ACE: An Actor Ensemble Algorithm for Continuous Control with Tree Search
Abstract: In this seminar, Hengshuai Yao presents a paper which he co-authored with Shangtong Zhang and Hao Chen, regarding propose actor ensemble algorithm, named ACE, for continuous control with a deterministic policy in reinforcement learning. This paper was accepted by the AAAI 2019 Conference on Artificial Intelligence.
Bio: Hengshuai studied reinforcement learning at Reinforcement Learning and Artificial Intelligence (RLAI) lab from 2008 to 2015 in a
PhDprogram at Department of Computing Science (supervised by Csaba Szepesvári), University of Alberta. His thesis is on model-based reinforcement learning with linear function approximation. He joined NCSoft game studio in San Francisco in 2016 working on reinforcement learning in games. He moved back to Canada in 2017 and joined Huawei Noah’s Ark Lab. Right now he is working on reinforcement learning and robotics.
February 22, 2 – 3 pm: Marc Bellemare
Location: CSC 3-33
Title: A geometric perspective on optimal representations in reinforcement learning
Abstract: In reinforcement learning, an important component of an agent is its representation of state: how it encodes raw state inputs into features that are useful to the process of decision-making. This talk presents some recent work on what constitutes a good representation, especially in the context of deep reinforcement learning, where the representation itself can be adapted to minimize prediction error.
Bio: Marc G. Bellemare is a research scientist at Google Brain in Montreal, Canada; CIFAR Learning in Machines & Brain Fellow; adjunct professor at McGill University; and was recently awarded a Canada CIFAR AI chair, held at the Montreal Institute for Learning Algorithms (Mila). He received his Ph.D. from the University of Alberta where he studied the concept of domain-independent agents and developed the highly-successful Arcade Learning Environment, the platform for AI research on Atari 2600 games. From 2013 to 2017 he was a research scientist at DeepMind where he made major contributions to the field of deep reinforcement learning.
Are you interested in presenting at an AI Seminar? If so, please contact the current organizer, Juliano Rabelo, at firstname.lastname@example.org.