Patent · US Active

Electronic apparatus and compression method for artificial neural network

US11270207B2 · kind B2 · utility

0Cited by
1References
9Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJan 22, 2019
Grant dateMar 8, 2022
Priority date
Expiry dateAug 19, 2040

Classification

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

Abstract

An electronic apparatus and a compression method for an artificial neural network are provided. The compression method is adapted for the artificial neural network with a plurality of convolution layers. The compression method includes: setting a first pruning layer for coupling the first pruning layer to Lth convolution layer, where the first pruning layer has a plurality of first weighting values and each of the first weighting values corresponds to each of a plurality of channels of the Lth convolution layer; tuning the first weighting values, selecting a part of the channels of the Lth convolution layer to be at least one first redundancy channel according to the first weighting values, and generating a compressed Lth convolution layer by deleting the at least one first redundancy channel; and removing the first pruning layer, and generating a first compressed artificial neural network.

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