News for hackers. Stuff that matters.

A comment on Stanford Stats 385: Theories of Deep Learning.

Re:Stanford Stats 385: Theories of Deep Learning by AlexCoventry on Tuesday November 07, 2017 @10:37PM (#15649746)
I'm a bit surprised that Soatto's and Tishby's papers aren't on the reading list (https://stats385.github.io/readings). I think they have some of the most interesting theories, at the moment, about why Deep Learning works.

https://arxiv.org/abs/1706.01350

https://openreview.net/pdf?id=ry_WPG-A-

[ Parent | on HN ]
Re:Stanford Stats 385: Theories of Deep Learning by trashtoss on Wednesday November 08, 2017 @10:52AM (#15653592)
Is anyone looking into/using algebraic topology and sheaves to analyze or interpret these deep networks?
[ Parent | on HN ]