Patent · US Active

Method and system for quantifying semantic variance between neural network representations

US12283082B1 · kind B1 · utility

0Cited by
0References
8Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 30, 2024
Grant dateApr 22, 2025
Priority date
Expiry dateApr 30, 2044

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V10/82
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method and system for quantifying semantic variance between neural network representations is provided. Two neural network representations to be compared are first extracted, the weight of each filter in an intermediate layer corresponding to each semantic concept is learned on a reference dataset using the Net2Vec method, then set IoU of each representation for all semantic concepts in the reference dataset are calculated, and finally variance between the set IoU of the two representations for all the semantic concepts are integrated to obtain semantic variance between the two neural network representations. The method solves the problem of lack of accurate measurement on the variance between neural network representations on a semantic information level, and has an accurate measurement effect.

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