Patent · US Active

Learning non-differentiable weights of neural networks using evolutionary strategies

US11676035B2 · kind B2 · utility

0Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJan 23, 2020
Grant dateJun 13, 2023
Priority date
Expiry dateDec 16, 2040

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 training a neural network. The neural network has a plurality of differentiable weights and a plurality of non-differentiable weights. One of the methods includes determining trained values of the plurality of differentiable weights and the non-differentiable weights by repeatedly performing operations that include determining an update to the current values of the plurality of differentiable weights using a machine learning gradient-based training technique and determining, using an evolution strategies (ES) technique, an update to the current values of a plurality of distribution parameters.

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