Information Theoretic Interpretation of Deep learning
arXiv:1803.07980v22 citations
Originality Synthesis-oriented
AI Analysis
This work provides a theoretical interpretation for researchers in deep learning, but it is incremental as it builds on existing studies without introducing new methods or data.
The authors addressed the interpretation of deep learning dynamics by analyzing prior experimental results and proposing a conjecture to explain conflicting findings in the literature.
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].