Information Theoretic Interpretation of Deep learning

Download PDF
Open Webpage

Tianchen Zhao

Published: 2018, Last Modified: 13 Nov 2024CoRR 2018EveryoneRevisionsBibTeXCC BY-SA 4.0
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].