A new hybrid neural network classifier based on adaptive neuron and multiplicative neuron

Basit Öğe Kaydı
dc.authoridkolay, erdinc/0000-0001-7436-3152
dc.authoridTUNC, Taner/0000-0002-5548-8475
dc.contributor.authorKolay, Erdinc
dc.contributor.authorTunc, Taner
dc.date.accessioned2025-03-23T19:44:35Z
dc.date.available2025-03-23T19:44:35Z
dc.date.issued2023
dc.departmentSinop Üniversitesi
dc.description.abstractNeural network (NN) classifiers are very popular tools for solving classification tasks. Mostly known NN classifier is a multilayer perceptron (MLP). Although MLP has a good correct classification ratio, its structure could be very complex and network training may work for a long time. Pi-sigma NN (PSNN) is higher-order NN (HONN), which used higher-order correlations among the input components to establish a HONN, and the PSNN utilizes the product of neurons as the output units. By contrast with MLP and PSNN, single multiplicative neuron (SMN) is simple concerning its structure and mathematical model. The absence of the hidden layer(s) could be an advantage for easy implementation, and the mathematical model can be easily interpreted. In this paper, we propose a new hybrid NN classifier based on simple adaptive neurons and SMN which form the SMN as a whole, where input units are constituted by adaptive neurons. In contrast with conventional NN, our proposed classifier can use fewer learning parameters. To train this network, we use a modified particle swarm optimization (MPSO) algorithm. For the investigation of the generalization capability of the proposed classifier, we compare this method to other NN classifiers: MLP and PSNN together with other classification procedure classifiers.
dc.identifier.doi10.1007/s00500-021-06093-6
dc.identifier.endpage1808
dc.identifier.issn1432-7643
dc.identifier.issn1433-7479
dc.identifier.issue3
dc.identifier.scopus2-s2.0-85112593337
dc.identifier.scopusqualityQ1
dc.identifier.startpage1797
dc.identifier.urihttps://doi.org/10.1007/s00500-021-06093-6
dc.identifier.urihttps://hdl.handle.net/11486/6972
dc.identifier.volume27
dc.identifier.wosWOS:000682428800001
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.language.isoen
dc.publisherSpringer
dc.relation.ispartofSoft Computing
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_WOS_20250323
dc.subjectClassification
dc.subjectMultilayer perceptron
dc.subjectPi-sigma neural network
dc.subjectMultiplicative neuron
dc.subjectParticle swarm optimization
dc.titleA new hybrid neural network classifier based on adaptive neuron and multiplicative neuron
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu