Patent · US Active

Adversarial training of neural networks

US10521718B1 · kind B1 · utility

10Cited by
1References
14Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 28, 2016
Grant dateDec 31, 2019
Priority date
Expiry dateMay 7, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/044
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for adversarial training of a neural network. One of the methods includes obtaining a plurality of training inputs; and training the neural network on each of the training inputs, comprising, for each of the training inputs: processing the training input using the neural network to determine a neural network output for the training input; applying a perturbation to the training input to generate an adversarial perturbation of the training input; processing the adversarial perturbation of the training input using the neural network to determine a neural network output for the adversarial perturbation; and adjusting the current values of the parameters of the neural network by performing an iteration of a neural network training procedure to optimize an adversarial objective function.

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