University of Cambridge > Talks.cam > Machine Learning @ CUED > Implicit Representation Networks

Implicit Representation Networks

Download to your calendar using vCal

If you have a question about this talk, please contact Dr Jes Frellsen .

I’ll discuss some thoughts on deep learning and finding low dimensional representations of data. I’ll discuss some novel ways to train deep networks and also argue that the standard autoencoder structure is not optimal.

This talk is part of the Machine Learning @ CUED series.

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

Š 2006-2025 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity