Back-propagation algorithm with variable adaptive momentum

dc.contributor.authorHameed, Alaa Ali
dc.contributor.authorKarlik, Bekir
dc.contributor.authorSalman, Mohammad Shukri
dc.date.accessioned2020-03-26T19:23:11Z
dc.date.available2020-03-26T19:23:11Z
dc.date.issued2016
dc.departmentSelçuk Üniversitesien_US
dc.description.abstractIn this paper, we propose a novel machine learning classifier by deriving a new adaptive momentum back-propagation (BP) artificial neural networks algorithm. The proposed algorithm is a modified version of the BP algorithm to improve its convergence behavior in both sides, accelerate the convergence process for accessing the optimum steady-state and minimizing the error misadjustment to improve the recognized patterns superiorly. This algorithm is controlled by the learning rate parameter which is dependent on the eigenvalues of the autocorrelation matrix of the input. It provides low error performance for the weights update. To discuss the performance measures of this proposed algorithm and the other supervised learning algorithms such as k-nearest neighbours (k-NN), Naive Bayes (NB), linear discriminant analysis (LDA), support vector machines (SVM), BP, and BP with adaptive momentum (PBPAM) have been compared in term of speed of convergence, Sum of Squared Error (SSE), and accuracy by implementing benchmark problem - XOR and seven datasets from UCI repository. (C) 2016 Elsevier B.V. All rights reserved.en_US
dc.identifier.doi10.1016/j.knosys.2016.10.001en_US
dc.identifier.endpage87en_US
dc.identifier.issn0950-7051en_US
dc.identifier.issn1872-7409en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage79en_US
dc.identifier.urihttps://dx.doi.org/10.1016/j.knosys.2016.10.001
dc.identifier.urihttps://hdl.handle.net/20.500.12395/33302
dc.identifier.volume114en_US
dc.identifier.wosWOS:000389396800007en_US
dc.identifier.wosqualityQ1en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherELSEVIER SCIENCE BVen_US
dc.relation.ispartofKNOWLEDGE-BASED SYSTEMSen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.selcuk20240510_oaigen_US
dc.subjectAdaptive momentumen_US
dc.subjectBack-propagationen_US
dc.subjectSupervised learningen_US
dc.subjectNeural networken_US
dc.titleBack-propagation algorithm with variable adaptive momentumen_US
dc.typeArticleen_US

Dosyalar