Patent · US Active

Compression of deep neural networks with proper use of mask

US10832123B2 · kind B2 · utility

3Cited by
1References
9Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 26, 2016
Grant dateNov 10, 2020
Priority date
Expiry dateJul 19, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/09
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The present invention relates to artificial neural networks, for example, deep neural networks. In particular, the present invention relates to a compression method for deep neural networks with proper use of mask and the device thereof. More specifically, the present invention relates to how to compress dense neural networks into sparse neural networks while maintaining or even improving the accuracy of the neural networks after compression.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.