1

When reading up on deep learning from various sources, one is often presented with the notion that deep learning is essentially a black box: A set of recipes, heuristics and empirical best practices that have been found to often work, but where the mechanism by which good results are achieved is usually not well understood. See for example http://www.nature.com/news/can-we-open-the-black-box-of-ai-1.20731.

I am looking specifically for resources (e.g. specific papers or research groups working in the field) of how this is not the case, i.e. work aimed at understanding why deep learning techniques work, both in the backward and forward direction.

I know about work on optimizing the input to a network in such a way as to activate some unit maximally (see http://yosinski.com/deepvis) and this seems interesting, but that's also a rather descriptive than mechanistic approach.

I would greatly appreciate any pointers!

fns
  • 11
  • 1
  • What research have you done? Have you searched this site and read other questions that talk about deep learning? You'll find some references at the highest-voted question in the [tag:machine-learning] tag. That should be enough to get you an entry point into the literature; you can then use Google Scholar to look for other papers on the subject. See also https://cs.stackexchange.com/a/48883/755. – D.W. Jun 14 '17 at 16:09

0 Answers0