Patent · US Active

Methods and apparatus to implement parallel architectures for neural network classifiers

US12260630B2 · kind B2 · utility

0Cited by
2References
24Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 25, 2021
Grant dateMar 25, 2025
Priority date
Expiry dateJan 9, 2044

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V10/806
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, apparatus, systems, and articles of manufacture are disclosed to implement parallel architectures for neural network classifiers. An example non-transitory computer readable medium comprises instructions that, when executed, cause a machine to at least: process a first stream using first neural network blocks, the first stream based on an input image; process a second stream using second neural network blocks, the second stream based on the input image; fuse a result of the first neural network blocks and the second neural network blocks; perform average pooling on the fused result; process a fully connected layer based on the result of the average pooling; and classify the image based on the output of the fully connected layer.

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