Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank

Unknown Journal, (2017)

Cited by: 0|Views5

Abstract:

Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks. Empirical results have shown that neural networks with weight matrices of LDR matrices, referred as LDR neural networks, can achieve significant reduction in space and computational complexity whil...More

Code:

Data:

ZH
Get fulltext within 24h
Bibtex
Your rating :
0

 

Tags
Comments