Patent · US Active

Regularization relaxation scheme

US10438129B1 · kind B1 · utility

2Cited by
3References
17Claims
0Family size

Assignee

Inventors

Key dates

Filing dateDec 30, 2014
Grant dateOct 8, 2019
Priority date
Expiry dateOct 11, 2036

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/00
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training machine learning systems. One of the methods includes receiving a plurality of training examples; and training a machine learning system on each of the plurality of training examples to determine trained values for weights of a machine learning model, wherein training the machine learning system comprises: assigning an initial value for a regularization penalty for a particular weight for a particular feature; and adjusting the initial value for the regularization penalty for the particular weight for the particular feature during the training of the machine learning system.

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