Patent · US Active

Deep learning internal state index-based search and classification

US11676579B2 · kind B2 · utility

1Cited by
51References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateOct 16, 2020
Grant dateJun 13, 2023
Priority date
Expiry dateApr 14, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L2015/081
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems and methods are disclosed for generating internal state representations of a neural network during processing and using the internal state representations for classification or search. In some embodiments, the internal state representations are generated from the output activation functions of a subset of nodes of the neural network. The internal state representations may be used for classification by training a classification model using internal state representations and corresponding classifications. The internal state representations may be used for search, by producing a search feature from an search input and comparing the search feature with one or more feature representations to find the feature representation with the highest degree of similarity.

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