Patent · US Active

Minimum error rate training with a large number of features for machine learning

US8645119B2 · kind B2 · utility

7Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 26, 2008
Grant dateFeb 4, 2014
Priority date
Expiry dateMar 27, 2032

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06F40/49
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems, methods, and apparatuses including computer program products for machine learning. A method is provided that includes determining model parameters for a plurality of feature functions for a linear machine learning model, ranking the plurality of feature functions according to a quality criterion, and selecting, using the ranking, a group of feature functions from the plurality of feature functions to update with the determined model parameters.

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