Publication

Compressing deep neural networks by matrix product operators

返回学术发表
Compressing deep neural networks by matrix product operators 论文配图

Ze-Feng Gao*,Song Cheng*, Rong-Qiang He, Zhi-Yuan Xie#, Hui-Hai Zhao#, Zhong-Yi Lu#, Tao Xiang#

Physical Review Research 2 (2), 023300, 2020

摘要

In this paper, we show that neural network can be effectively solved by representing linear transformations with matrix product operators (MPOs), which is a tensor network originally proposed in physics to characterize the short-range entanglement in one-dimensional quantum states.