paper

Information Theoretic Interpretation of Deep learning

arXiv:1803.07980

Abstract

We interpret part of the experimental results of Shwartz-Ziv and Tishby [2017]. Inspired by these results, we established a conjecture of the dynamics of the machinary of deep neural network. This conjecture can be used to explain the counterpart result by Saxe et al. [2018].

17 pages, 7 figures

Information Theoretic Interpretation of Deep learning · wovepaper