Patent · US Active

Techniques for identification of out-of-distribution input data in neural networks

US11978258B2 · kind B2 · utility

0Cited by
0References
41Claims
0Family size

Assignee

Inventors

Key dates

Filing dateApr 6, 2021
Grant dateMay 7, 2024
Priority date
Expiry dateNov 14, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/044
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Apparatuses, systems, and techniques to identify out-of-distribution input data in one or more neural networks. In at least one embodiment, a technique includes training one or more neural networks to infer a plurality of characteristics about input information based, at least in part, on the one or more neural networks being independently trained to infer each of the plurality of characteristics about the input information.

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