Comparing Dynamics: Deep Neural Networks versus Glassy Systems

international conference on machine learning, 2018.

Cited by: 2|Bibtex|Views199|DOI:https://doi.org/10.1088/1742-5468/ab3281
EI
Other Links: dblp.uni-trier.de|academic.microsoft.com|arxiv.org

Abstract:

We analyze numerically the training dynamics of deep neural networks (DNN) by using methods developed in statistical physics of glassy systems. The two main issues we address are the complexity of the loss-landscape and of the dynamics within it, and to what extent DNNs share similarities with glassy systems. Our findings, obtained for di...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments