Patent · US Active

Neural network training method for memristor memory for memristor errors

US11449754B1 · kind B1 · utility

2Cited by
0References
6Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 16, 2022
Grant dateSep 20, 2022
Priority date
Expiry dateFeb 16, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG11C13/0007
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The present invention discloses a neural network training method for a memristor memory for memristor errors, which is mainly used for solving the problem of decrease in inference accuracy of a neural network based on the memristor memory due to a process error and a dynamic error. The method comprises the following steps: performing modeling on a conductance value of a memristor under the influence of the process error and the dynamic error, and performing conversion to obtain a distribution of corresponding neural network weights; constructing a prior distribution of the weights by using the weight distribution obtained after modeling, and performing Bayesian neural network training based on variational inference to obtain a variational posterior distribution of the weights; and converting a mean value of the variational posterior of the weights into a target conductance value of the memristor memory.

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