Patent · US Active

Optimized neural network data organization

US11080152B2 · kind B2 · utility

1Cited by
3References
18Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 15, 2019
Grant dateAug 3, 2021
Priority date
Expiry dateMay 15, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F2201/805
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

In some implementations, the present disclosure relates to a method. The method includes obtaining a set of weights for a neural network comprising a plurality of nodes and a plurality of connections between the plurality of nodes. The method also includes identifying a first subset of weights and a second subset of weights based on the set of weights. The first subset of weights comprises weights that used by the neural network. The second subset of weights comprises weights that are prunable. The method further includes storing the first subset of weights in a first portion of a memory. A first error correction code is used for the first portion of the memory. The method further includes storing the second subset of weights in a second portion of the memory. A second error correction code is used for the second portion of the memory. The second error correction code is weaker than the first error correction code.

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