Patent · US Active

Passive pruning of filters in a convolutional neural network

US10832136B2 · kind B2 · utility

3Cited by
0References
15Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 9, 2017
Grant dateNov 10, 2020
Priority date
Expiry dateJul 9, 2039

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH03H2222/04
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods and systems for pruning a convolutional neural network (CNN) include calculating a sum of weights for each filter in a layer of the CNN. The filters in the layer are sorted by respective sums of weights. A set of m filters with the smallest sums of weights is filtered to decrease a computational cost of operating the CNN. The pruned CNN is retrained to repair accuracy loss that results from pruning the filters.

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