Patent · US Active

Ranking approach to train deep neural nets for multilabel image annotation

US9552549B1 · kind B1 · utility

32Cited by
7References
19Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 28, 2014
Grant dateJan 24, 2017
Priority date
Expiry dateSep 4, 2035

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/09
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems and techniques are provided for a ranking approach to train deep neural nets for multilabel image annotation. Label scores may be received for labels determined by a neural network for training examples. Each label may be a positive label or a negative label for the training example. An error of the neural network may be determined based on a comparison, for each of the training examples, of the label scores for positive labels and negative labels for the training example and a semantic distance between each positive label and each negative label for the training example. Updated weights may be determined for the neural network based on a gradient of the determined error of the neural network. The updated weights may be applied to the neural network to train the neural network.

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