Patent · US Active

Systems and methods for pruning neural networks for resource efficient inference

US11315018B2 · kind B2 · utility

4Cited by
15References
21Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 17, 2017
Grant dateApr 26, 2022
Priority date
Expiry dateMar 17, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/096
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method, computer readable medium, and system are disclosed for neural network pruning. The method includes the steps of receiving first-order gradients of a cost function relative to layer parameters for a trained neural network and computing a pruning criterion for each layer parameter based on the first-order gradient corresponding to the layer parameter, where the pruning criterion indicates an importance of each neuron that is included in the trained neural network and is associated with the layer parameter. The method includes the additional steps of identifying at least one neuron having a lowest importance and removing the at least one neuron from the trained neural network to produce a pruned neural network.

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