Compressing deep neural networks by matrix product operators

11 Apr 2019Ze-Feng GaoSong ChengRong-Qiang HeZ. Y. XieHui-Hai ZhaoZhong-Yi LuTao Xiang

A deep neural network is a parametrization of a multilayer mapping of signals in terms of many alternatively arranged linear and nonlinear transformations. The linear transformations, which are generally used in the fully connected as well as convolutional layers, contain most of the variational parameters that are trained and stored... (read more)

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper