New complex-valued activation functions

Basit Öğe Kaydı
dc.authoridPeters, James/0000-0002-1026-4638
dc.authoridTAS, Nihal/0000-0002-4535-4019
dc.authoridOZGUR, Nihal/0000-0002-8152-1830
dc.contributor.authorOzgui, Nihal
dc.contributor.authorTas, Nihal
dc.contributor.authorPeters, James F.
dc.date.accessioned2025-07-03T21:25:45Z
dc.date.issued2020
dc.departmentBalıkesir Üniversitesi
dc.description.abstractWe present a new type of activation functions for a complex-valued neural network (CVNN). A proposed activation function is constructed such that it fixes a given ellipse. We obtain an application to a complex-valued Hopfield neural network (CVHNN) using a special form of the introduced complex functions as an activation function. Considering the interesting geometric properties of the plane curve ellipse such as focusing property, we emphasize that these properties may have possible applications in various neural networks.
dc.description.sponsorshipNatural Sciences & Engineering Research Council of Canada (NSERC) [185986]; Scientific and Technological Research Council of Turkey (TBTAK) Scientific Human Resources Development (BIDEB) [2221-1059B211402463]; Instituto Nazionale di Alta Matematica (INdAM)Francesco Severi, Gruppo Nazionale per le Strutture Algebriche, Geometriche e Loro Applicazioni [9 920160 000362, U 2016/000036]
dc.description.sponsorshipThe authors would like to thank the anonymous referees for their comments that helped us improve this article. The research by J.F. Peters has been supported by y the Natural Sciences & Engineering Research Council of Canada (NSERC) discovery grant 185986, Scientific and Technological Research Council of Turkey (TBTAK) Scientific Human Resources Development (BIDEB) under grant no: 2221-1059B211402463, and Instituto Nazionale di Alta Matematica (INdAM)Francesco Severi, Gruppo Nazionale per le Strutture Algebriche, Geometriche e Loro Applicazioni grant 9 920160 000362, n. prot U 2016/000036.
dc.identifier.doi10.11121/ijocta.01.2020.00756
dc.identifier.endpage72
dc.identifier.issn2146-0957
dc.identifier.issn2146-5703
dc.identifier.issue1
dc.identifier.scopusqualityQ2
dc.identifier.startpage66
dc.identifier.urihttps://doi.org/10.11121/ijocta.01.2020.00756
dc.identifier.urihttps://hdl.handle.net/20.500.12462/21657
dc.identifier.volume10
dc.identifier.wosWOS:000871121500008
dc.identifier.wosqualityN/A
dc.indekslendigikaynakWeb of Science
dc.language.isoen
dc.publisherRamazan Yaman
dc.relation.ispartofInternational Journal of Optimization and Control-Theories & Applications-Ijocta
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WOS_20250703
dc.subjectComplex valued neural network
dc.subjectComplex-valued Hopfield neural network
dc.subjectActivation function
dc.subjectFixed ellipse
dc.titleNew complex-valued activation functions
dc.typeArticle

Dosyalar

Koleksiyon

WOS İndeksli Yayınlar Koleksiyonu