University of Cambridge > Talks.cam > Artificial Intelligence Research Group Talks (Computer Laboratory) > Some ideas on neural network modulation

Some ideas on neural network modulation

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Mateja Jamnik.

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.

This talk is part of the Artificial Intelligence Research Group Talks (Computer Laboratory) series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2020 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity