skip to content

Department of Computer Science and Technology

Date: 
Tuesday, 18 February, 2020 - 13:00 to 14:00
Speaker: 
Ben Day (Department of Computer Science and Technology)
Venue: 
GS15, Computer Laboratory, William Gates Building
Abstract: 

This talk is in the ‘perhaps you had an idea?’ and ‘perhaps you are stuck?’ categories.

Broadly, the talk will be about heterogeneity in the confusion matrix and what we can hope to do with it. Progressive neural networks will be linked to the developmental pathway of style transfer models and feature-wise conditioning in general. We’ll touch on the methodology of the lottery ticket hypothesis and related works, as well as new developments in continuously sparsifying neural networks, as mechanisms with better-restricted capacity. New results from work done with Cristian Bodnar and Stanislav Fort will be discussed.

Series: 
Artificial Intelligence Research Group Talks (Computer Laboratory)

Upcoming seminars