Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.11851/7152
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Efe, Mehmet Önder | - |
dc.date.accessioned | 2021-09-11T15:55:49Z | - |
dc.date.available | 2021-09-11T15:55:49Z | - |
dc.date.issued | 2008 | en_US |
dc.identifier.issn | 1370-4621 | - |
dc.identifier.issn | 1573-773X | - |
dc.identifier.uri | https://doi.org/10.1007/s11063-008-9082-0 | - |
dc.identifier.uri | https://hdl.handle.net/20.500.11851/7152 | - |
dc.description.abstract | Feedforward neural network structures have extensively been considered in the literature. In a significant volume of research and development studies hyperbolic tangent type of a neuronal nonlinearity has been utilized. This paper dwells on the widely used neuronal activation functions as well as two new ones composed of sines and cosines, and a sinc function characterizing the firing of a neuron. The viewpoint here is to consider the hidden layer(s) as transforming blocks composed of nonlinear basis functions, which may assume different forms. This paper considers 8 different activation functions which are differentiable and utilizes Levenberg-Marquardt algorithm for parameter tuning purposes. The studies carried out have a guiding quality based on empirical results on several training data sets. | en_US |
dc.description.sponsorship | TOBB Economics and Technology UniversityTOBB Ekonomi ve Teknoloji University [ETU BAP-2006/04]; TUBITAKTurkiye Bilimsel ve Teknolojik Arastirma Kurumu (TUBITAK) [107E137] | en_US |
dc.description.sponsorship | This work was supported by TOBB Economics and Technology University, BAP Program, under contract no ETU BAP-2006/04 and TUBITAK contract no 107E137. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Springer | en_US |
dc.relation.ispartof | Neural Processing Letters | en_US |
dc.rights | info:eu-repo/semantics/openAccess | en_US |
dc.subject | activation functions | en_US |
dc.subject | dynamical system identification | en_US |
dc.subject | Levenberg-Marquardt algorithm | en_US |
dc.title | Novel Neuronal Activation Functions for Feedforward Neural Networks | en_US |
dc.type | Article | en_US |
dc.department | Faculties, Faculty of Engineering, Department of Electrical and Electronics Engineering | en_US |
dc.department | Fakülteler, Mühendislik Fakültesi, Elektrik ve Elektronik Mühendisliği Bölümü | tr_TR |
dc.identifier.volume | 28 | en_US |
dc.identifier.issue | 2 | en_US |
dc.identifier.startpage | 63 | en_US |
dc.identifier.endpage | 79 | en_US |
dc.authorid | 0000-0002-5992-895X | - |
dc.identifier.wos | WOS:000259575500001 | en_US |
dc.identifier.scopus | 2-s2.0-52949151520 | en_US |
dc.institutionauthor | Önder Efe, Mehmet | - |
dc.identifier.doi | 10.1007/s11063-008-9082-0 | - |
dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | en_US |
dc.identifier.scopusquality | Q2 | - |
item.openairetype | Article | - |
item.languageiso639-1 | en | - |
item.grantfulltext | none | - |
item.fulltext | No Fulltext | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.cerifentitytype | Publications | - |
crisitem.author.dept | 02.5. Department of Electrical and Electronics Engineering | - |
Appears in Collections: | Elektrik ve Elektronik Mühendisliği Bölümü / Department of Electrical & Electronics Engineering Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection |
CORE Recommender
SCOPUSTM
Citations
10
checked on Dec 21, 2024
WEB OF SCIENCETM
Citations
12
checked on Nov 2, 2024
Page view(s)
46
checked on Dec 23, 2024
Google ScholarTM
Check
Altmetric
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.