Statements in which the resource exists.
SubjectPredicateObjectContext
pubmed-article:14692636rdf:typepubmed:Citationlld:pubmed
pubmed-article:14692636lifeskim:mentionsumls-concept:C1882071lld:lifeskim
pubmed-article:14692636lifeskim:mentionsumls-concept:C0542193lld:lifeskim
pubmed-article:14692636lifeskim:mentionsumls-concept:C0542341lld:lifeskim
pubmed-article:14692636lifeskim:mentionsumls-concept:C0179126lld:lifeskim
pubmed-article:14692636lifeskim:mentionsumls-concept:C0348080lld:lifeskim
pubmed-article:14692636lifeskim:mentionsumls-concept:C0175671lld:lifeskim
pubmed-article:14692636pubmed:issue7lld:pubmed
pubmed-article:14692636pubmed:dateCreated2003-12-24lld:pubmed
pubmed-article:14692636pubmed:abstractTextIn this paper, we investigate the universal approximation property of Radial Basis Function (RBF) networks. We show that RBFs are not required to be integrable for the REF networks to be universal approximators. Instead, RBF networks can uniformly approximate any continuous function on a compact set provided that the radial basis activation function is continuous almost everywhere, locally essentially bounded, and not a polynomial. The approximation in L(p)(micro)(1 < or = p < infinity) space is also discussed. Some experimental results are reported to illustrate our findings.lld:pubmed
pubmed-article:14692636pubmed:commentsCorrectionshttp://linkedlifedata.com/r...lld:pubmed
pubmed-article:14692636pubmed:languageenglld:pubmed
pubmed-article:14692636pubmed:journalhttp://linkedlifedata.com/r...lld:pubmed
pubmed-article:14692636pubmed:citationSubsetIMlld:pubmed
pubmed-article:14692636pubmed:statusMEDLINElld:pubmed
pubmed-article:14692636pubmed:monthSeplld:pubmed
pubmed-article:14692636pubmed:issn0893-6080lld:pubmed
pubmed-article:14692636pubmed:authorpubmed-author:LiaoYiYlld:pubmed
pubmed-article:14692636pubmed:authorpubmed-author:FangShu-Chern...lld:pubmed
pubmed-article:14692636pubmed:authorpubmed-author:NuttleHenry...lld:pubmed
pubmed-article:14692636pubmed:issnTypePrintlld:pubmed
pubmed-article:14692636pubmed:volume16lld:pubmed
pubmed-article:14692636pubmed:ownerNLMlld:pubmed
pubmed-article:14692636pubmed:authorsCompleteYlld:pubmed
pubmed-article:14692636pubmed:pagination1019-28lld:pubmed
pubmed-article:14692636pubmed:dateRevised2009-3-3lld:pubmed
pubmed-article:14692636pubmed:meshHeadingpubmed-meshheading:14692636...lld:pubmed
pubmed-article:14692636pubmed:year2003lld:pubmed
pubmed-article:14692636pubmed:articleTitleRelaxed conditions for radial-basis function networks to be universal approximators.lld:pubmed
pubmed-article:14692636pubmed:affiliationOperations Research and Industrial Engineering, North Carolina State University, Raleigh, NC 27695-7906, USA. yliao2@eos.ncsu.edulld:pubmed
pubmed-article:14692636pubmed:publicationTypeJournal Articlelld:pubmed
http://linkedlifedata.com/r...pubmed:referesTopubmed-article:14692636lld:pubmed