Basit öğe kaydını göster

dc.contributor.authorAltan, Gökhan
dc.contributor.authorAlkan, Sertan
dc.contributor.authorBaleanu, Dumitru
dc.date.accessioned2022-11-28T12:29:12Z
dc.date.available2022-11-28T12:29:12Z
dc.date.issued2022en_US
dc.identifier.citationAltan, G., Alkan, S., Baleanu, D. (2022). A novel fractional operator application for neural networks using proportional Caputo derivative. Neural Comput & Applic. https://doi.org/10.1007/s00521-022-07728-xen_US
dc.identifier.urihttps://doi.org/10.1007/s00521-022-07728-x
dc.identifier.urihttps://hdl.handle.net/20.500.12508/2342
dc.description.abstractIn machine learning models, one of the most popular models is artificial neural networks. The activation function is one of the important parameters of neural networks. In this paper, the sigmoid function is used as an activation function with a fractional derivative approach to minimize the convergence error in backpropagation and to maximize the generalization performance of neural networks. The proportional Caputo definition is considered a fractional derivative. We evaluated three neural network models on the usage of the proportional Caputo derivative. The results show that the proportional Caputo derivative approach has higher classification accuracy than traditional derivative models in backpropagation for neural networks with and without L2 regularization.en_US
dc.language.isoengen_US
dc.publisherSpringeren_US
dc.relation.isversionof10.1007/s00521-022-07728-xen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectActivation functionen_US
dc.subjectFractional orderen_US
dc.subjectNeural networksen_US
dc.subjectProportional caputo derivativeen_US
dc.subject.classificationFractional-Order System
dc.subject.classificationChaotic Dynamics
dc.subject.classificationMemristors
dc.subject.classificationComputer Science
dc.subject.classificationMathematics - Dynamical Systems & Time Dependence - Global Exponential Stability
dc.subject.otherStability
dc.subject.otherBackpropagation
dc.subject.otherChemical activation
dc.subject.otherActivation functions
dc.subject.otherCaputo derivatives
dc.subject.otherConvergence errors
dc.subject.otherFractional derivatives
dc.subject.otherFractional operators
dc.subject.otherFractional order
dc.subject.otherMachine learning models
dc.subject.otherNeural-networks
dc.subject.otherProportional caputo derivative
dc.subject.otherSigmoid function
dc.subject.otherNeural networks
dc.titleA novel fractional operator application for neural networks using proportional Caputo derivativeen_US
dc.typearticleen_US
dc.relation.journalNeural Computing and Applicationsen_US
dc.contributor.departmentMühendislik ve Doğa Bilimleri Fakültesi -- Metalurji ve Malzeme Mühendisliği Bölümüen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.contributor.isteauthorAltan, Gökhan
dc.contributor.isteauthorAlkan, Sertan
dc.relation.indexWeb of Science - Scopusen_US
dc.relation.indexWeb of Science Core Collection - Science Citation Index Expanded


Bu öğenin dosyaları:

Thumbnail

Bu öğe aşağıdaki koleksiyon(lar)da görünmektedir.

Basit öğe kaydını göster