Patent · US Active

Method for training a learning machine having a deep multi-layered network with labeled and unlabeled training data

US8234228B2 · kind B2 · utility

22Cited by
1References
12Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 6, 2009
Grant dateJul 31, 2012
Priority date
Expiry dateDec 27, 2030

Classification

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

Abstract

The invention includes a method for training a learning machine having a deep multi-layered network, with labeled and unlabeled training data. The deep multi-layered network is a network having multiple layers of non-linear mapping. The method generally includes applying unsupervised embedding to any one or more of the layers of the deep network. The unsupervised embedding is operative as a semi-supervised regularizer in the deep network.

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