Skip to main navigation Skip to search Skip to main content

The bounds on the risk for sets of unbounded nonnegative functions on possibility space

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Statistical learning theory on probability space is an important part of Machine Learning. Based on the key theorem, the bounds of uniform convergence have significant meaning. These bounds determine generalization ability of the learning machines utilizing the empirical risk minimization induction principle. In this paper, the bounds on the risk for sets of unbounded nonnegative functions on possibility space are discussed, and the rate of uniform convergence is estimated.

Original languageEnglish
Title of host publicationProceedings of 2011 International Conference on Machine Learning and Cybernetics, ICMLC 2011
PublisherIEEE Computer Society
Pages881-886
Number of pages6
ISBN (Print)9781457703065
DOIs
StatePublished - 2011
Externally publishedYes
Event10th International Conference on Machine Learning and Cybernetics, ICMLC 2011 - Guilin, Guangxi, China
Duration: 10 Jul 201113 Jul 2011

Publication series

NameProceedings - International Conference on Machine Learning and Cybernetics
Volume2
ISSN (Print)2160-133X
ISSN (Electronic)2160-1348

Conference

Conference10th International Conference on Machine Learning and Cybernetics, ICMLC 2011
Country/TerritoryChina
CityGuilin, Guangxi
Period10/07/1113/07/11

Keywords

  • Credibility measure
  • Possibility space
  • The bounds on the risk for unbounded nonnegative functions
  • The empirical risk
  • The expected risk

Fingerprint

Dive into the research topics of 'The bounds on the risk for sets of unbounded nonnegative functions on possibility space'. Together they form a unique fingerprint.

Cite this