Current students

Subscribe to Current students
Thursday, May 4, 2023 11:00 am - 12:00 pm EDT (GMT -04:00)

PhD Seminar • Artificial Intelligence | Computer Vision • Collision Cross-Entropy for Discriminative Deep Clustering

Please note: This PhD seminar will take place in DC 3317.

Zhongwen Zhang, PhD candidate
David R. Cheriton School of Computer Science

Supervisor: Professor Yuri Boykov

Monday, May 15, 2023 10:00 am - 11:00 am EDT (GMT -04:00)

Master’s Thesis Presentation • Artificial Intelligence • User-specific Explanations of AI Systems Attuned to Psychological Profiles: A User Study

Please note: This master’s thesis presentation will be given online.

Owen Chambers, Master’s candidate
David R. Cheriton School of Computer Science

Supervisors: Professors Robin Cohen, Maura R. Grossman

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.

Thursday, April 27, 2023 11:00 am - 12:00 pm EDT (GMT -04:00)

PhD Seminar • Artificial Intelligence • Towards a Better Understanding of Learning with Multiagent Teams

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.

photo of Professor Craig S. Kaplan holding two einstein tiles
Thursday, April 13, 2023

A trick of the hat — finding the elusive einstein tile

A nearly 60-year-old mathematical problem has finally been solved.

The story began last fall when David Smith, a retired print technician from Yorkshire, England, came upon a shape with a tantalizing property. The life-long tiling enthusiast discovered a 13-sided shape — dubbed the hat — that is able to fill the infinite plane without overlaps or gaps in a pattern that not only never repeats but also never can be made to repeat.

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.