Method and system for quantifying semantic variance between neural network representations
US12283082B1 · kind B1 · utility
Assignee
Inventors
Key dates
| Filing date | Apr 30, 2024 |
| Grant date | Apr 22, 2025 |
| Priority date | — |
| Expiry date | Apr 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.