Information Theoretic Interpretation of Deep learning
T. Zhao, и Y. Sun. (2018)cite arxiv:1803.07980Comment: 17 pages, 7 figures.
Аннотация
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.
Описание
[1803.07980] Information Theoretic Interpretation of Deep learning
%0 Generic
%1 zhao2018information
%A Zhao, Tianchen
%A Sun, Yuekai
%D 2018
%K dnn information-theory
%T Information Theoretic Interpretation of Deep learning
%U http://arxiv.org/abs/1803.07980
%X 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.
@misc{zhao2018information,
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].},
added-at = {2018-03-22T16:08:15.000+0100},
author = {Zhao, Tianchen and Sun, Yuekai},
biburl = {https://www.bibsonomy.org/bibtex/2c7d09b8db72844b9fb597b63a81d2ce1/rcb},
description = {[1803.07980] Information Theoretic Interpretation of Deep learning},
interhash = {5deff883b1ac978d68544cdd6bfcdc64},
intrahash = {c7d09b8db72844b9fb597b63a81d2ce1},
keywords = {dnn information-theory},
note = {cite arxiv:1803.07980Comment: 17 pages, 7 figures},
timestamp = {2018-03-22T16:08:15.000+0100},
title = {Information Theoretic Interpretation of Deep learning},
url = {http://arxiv.org/abs/1803.07980},
year = 2018
}