Patent · US Active

Method for implementing neural network model in heterogeneous computing platform and apparatus for performing the same

US11803733B2 · kind B2 · utility

0Cited by
2References
24Claims
0Family size

Assignee

Inventors

Key dates

Filing dateAug 3, 2020
Grant dateOct 31, 2023
Priority date
Expiry dateAug 25, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/0475
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method and apparatus for implementing a neural network model in a heterogeneous computing platform are disclosed. The method includes partitioning a neural network model into first sub-models based on a partition standard, obtaining second sub-models by merging at least a portion of the first sub-models based on characteristics of the first sub-models, and deploying the second sub-models.

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