Seminar

Please note: This PhD seminar will take place in DC 3317 and virtually over Zoom.

David Radke, PhD candidate
David R. Cheriton School of Computer Science

Supervisors: Professors Kate Larson, Tim Brecht

Thursday, April 20, 2023 1:00 pm - 2:00 pm EDT (GMT -04:00)

Seminar • Machine Learning • Backpropagation Beyond the Gradient

Please note: This seminar will take place in DC 2585.

Felix Dangel, Postdoctoral Researcher
Vector Institute for Artificial Intelligence

Popular deep learning frameworks prioritize computing the average mini-batch gradient. Yet, other quantities such as its variance or many approximations to the Hessian can be computed efficiently, and at the same time as the gradient mean. They are of great interest to researchers and practitioners, but implementing them is often burdensome or inefficient.

Please note: This PhD seminar will be given online.

David Radke, PhD candidate
David R. Cheriton School of Computer Science

Supervisors: Professors Kate Larson, Tim Brecht

While it has long been recognized that a team of individual learning agents can be greater than the sum of its parts, recent work has shown that larger teams are not necessarily more effective than smaller ones.

Monday, April 17, 2023 3:00 pm - 4:00 pm EDT (GMT -04:00)

PhD Seminar • Computer Graphics • A Projective Drawing System

Please note: This PhD seminar will take place online.

Greg Philbrick, PhD candidate
David R. Cheriton School of Computer Science

Supervisor: Professor Craig Kaplan

This paper treats the subject of pseudo-3D modeling (via drawing in projective coordinates). I'll talk about the authors’ methods, as well as my own exploration of pseudo-3D drawing techniques.