Patent · US Active

Automatic thresholds for neural network pruning and retraining

US12008474B2 · kind B2 · utility

0Cited by
5References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 9, 2020
Grant dateJun 11, 2024
Priority date
Expiry dateMay 18, 2041

Classification

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

Abstract

An embodiment includes a method, comprising: pruning a layer of a neural network having multiple layers using a threshold; and repeating the pruning of the layer of the neural network using a different threshold until a pruning error of the pruned layer reaches a pruning error allowance.

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