News for hackers. Stuff that matters.
Re:Information Theoretic Learning Auto-Encoders by goldenkey on Sunday April 10, 2016 @01:27PM (#11467172)
Very poorly documented. I could not figure out what the goal of the project is although it sounds like a codec that uses machine learning.
Re:Information Theoretic Learning Auto-Encoders by daveguy on Sunday April 10, 2016 @01:58PM (#11467361)
Not affiliated, but I found the paper. First link to gitxiv is the abstract of a paper on arxiv. Here is the paper with more detail:

http://arxiv.org/abs/1603.06653

Re:Information Theoretic Learning Auto-Encoders by eejr on Sunday April 10, 2016 @08:59PM (#11469022)
Hi, sorry for the poor documentation. But please, check out the paper the person above mentioned. We worked hard to make it as accessible as possible. Also, the core of our code is actually here: https://github.com/EderSantana/seya/blob/master/seya/layers/...

If you are a Keras (or Theano) dev it should be an easy read. If not, please drop us a note on github.