Measure Theoretic Results for Approximation by Neural Networks with Limited Weights
dc.contributor.author | Ismailov, V.E. | |
dc.contributor.author | Savaş, Ekrem | |
dc.date.accessioned | 2020-11-21T15:53:22Z | |
dc.date.available | 2020-11-21T15:53:22Z | |
dc.date.issued | 2017 | en_US |
dc.department | İstanbul Ticaret Üniversitesi | en_US |
dc.description.abstract | In 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.doi | 10.1080/01630563.2016.1254654 | en_US |
dc.identifier.endpage | 830 | en_US |
dc.identifier.issn | 0163-0563 | |
dc.identifier.issue | 7 | en_US |
dc.identifier.scopus | 2-s2.0-85017240763 | en_US |
dc.identifier.scopusquality | Q2 | en_US |
dc.identifier.startpage | 819 | en_US |
dc.identifier.uri | https://doi.org/10.1080/01630563.2016.1254654 | |
dc.identifier.uri | https://hdl.handle.net/11467/3559 | |
dc.identifier.volume | 38 | en_US |
dc.identifier.wos | WOS:000402005500001 | en_US |
dc.identifier.wosquality | Q3 | en_US |
dc.indekslendigikaynak | Web of Science | en_US |
dc.indekslendigikaynak | Scopus | en_US |
dc.language.iso | en | en_US |
dc.publisher | Taylor and Francis Inc. | en_US |
dc.relation.ispartof | Numerical Functional Analysis and Optimization | en_US |
dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | en_US |
dc.rights | info:eu-repo/semantics/closedAccess | en_US |
dc.subject | Activation function | en_US |
dc.subject | Borel measure | en_US |
dc.subject | density | en_US |
dc.subject | lightning bolt | en_US |
dc.subject | neural network | en_US |
dc.subject | orbit | en_US |
dc.subject | orthogonal measure | en_US |
dc.subject | weak convergence | en_US |
dc.title | Measure Theoretic Results for Approximation by Neural Networks with Limited Weights | en_US |
dc.type | Article | en_US |