Seminar

Subscribe to Seminar
Friday, June 24, 2022 1:00 pm - 2:00 pm EDT (GMT -04:00)

PhD Seminar • Machine Learning • Out-of-distribution Detection with Flow Generative Models

Please note: This PhD seminar will be given online.

Dihong Jiang, PhD candidate
David R. Cheriton School of Computer Science

Supervisor: Professor Yaoliang Yu

Out-of-distribution (OOD) data come from a distribution that is different from training data. Detecting OOD data contributes to secure deployment of machine learning models. Currently, deep generative models have been widely used as an unsupervised approach for OOD detection.

Wednesday, June 22, 2022 12:00 pm - 1:00 pm EDT (GMT -04:00)

PhD Seminar • Data Systems | NLP • Backward-compatibility for Neural NLP Models

Please note: This PhD seminar will be given online.

Yuqing Xie, PhD candidate
David R. Cheriton School of Computer Science

Supervisors: Professors Ming Li, Jimmy Lin

I would like to share the work I did during the internship with AWS AI about Backward-Compatibility NLP models. Behavior of deep neural networks can be inconsistent between different versions. Regressions during model update are a common cause of concern that often over-weigh the benefits in accuracy or efficiency gain. 

Friday, June 3, 2022 2:00 pm - 3:00 pm EDT (GMT -04:00)

PhD Seminar • Algorithms and Complexity • On Testing and Robust Characterization of Convexity

Please note: This PhD seminar will be given online.

Abhinav Bommireddi, PhD candidate
David R. Cheriton School of Computer Science

Supervisor: Professor Eric Blais

A body K ⊂ Rn is convex if and only if the line segment between any two points in K is completely contained within K or, equivalently, if and only if the convex hull of a set of points in K is contained within K.