@rcb

Information Theoretic Interpretation of Deep learning

, and . (2018)cite arxiv:1803.07980Comment: 17 pages, 7 figures.

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.

Description

[1803.07980] Information Theoretic Interpretation of Deep learning

Links and resources

Tags

community

  • @rcb
  • @achakraborty
@rcb's tags highlighted