Measure Theoretic Results for Approximation by Neural Networks with Limited Weights

dc.contributor.authorIsmailov, V.E.
dc.contributor.authorSavaş, Ekrem
dc.date.accessioned2020-11-21T15:53:22Z
dc.date.available2020-11-21T15:53:22Z
dc.date.issued2017en_US
dc.departmentİstanbul Ticaret Üniversitesien_US
dc.description.abstractIn this article, we study approximation properties of single hidden layer neural networks with weights varying in finitely many directions and with thresholds from an open interval. We obtain a necessary and simultaneously su?cient measure theoretic condition for density of such networks in the space of continuous functions. Further, we prove a density result for neural networks with a specifically constructed activation function and a fixed number of neurons. © 2017 Taylor & Francis.en_US
dc.identifier.doi10.1080/01630563.2016.1254654en_US
dc.identifier.endpage830en_US
dc.identifier.issn0163-0563
dc.identifier.issue7en_US
dc.identifier.scopus2-s2.0-85017240763en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.startpage819en_US
dc.identifier.urihttps://doi.org/10.1080/01630563.2016.1254654
dc.identifier.urihttps://hdl.handle.net/11467/3559
dc.identifier.volume38en_US
dc.identifier.wosWOS:000402005500001en_US
dc.identifier.wosqualityQ3en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherTaylor and Francis Inc.en_US
dc.relation.ispartofNumerical Functional Analysis and Optimizationen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectActivation functionen_US
dc.subjectBorel measureen_US
dc.subjectdensityen_US
dc.subjectlightning bolten_US
dc.subjectneural networken_US
dc.subjectorbiten_US
dc.subjectorthogonal measureen_US
dc.subjectweak convergenceen_US
dc.titleMeasure Theoretic Results for Approximation by Neural Networks with Limited Weightsen_US
dc.typeArticleen_US

Dosyalar