LYAPUNOV THEORY BASED ADAPTIVE LEARNING ALGORITHM FOR MULTILAYER NEURAL NETWORKS

Basit Öğe Kaydı
dc.authorid0000-0002-0619-549X
dc.contributor.authorAcir, Nurettin
dc.contributor.authorMenguc, Engin Cemal
dc.date.accessioned2019-08-01T13:38:39Z
dc.date.available2019-08-01T13:38:39Z
dc.date.issued2014
dc.departmentNiğde ÖHÜ
dc.description.abstractThis paper presents a novel weight updating algorithm for training of multilayer neural network (MLNN). The MLNN system is first linearized and then the design procedure is proposed as an inequality constraint optimization problem. A well selected Lyapunov function is suitably determined and integrated into the constraint function for satisfying asymptotic stability in the sense of Lyapunov. Thus, the convergence capability of training algorithm is improved by using a new analytical adaptation gain rate which has the ability to adaptively adjust itself depending on a sequential square error rate. The proposed algorithm is compared with two types of backpropagation algorithms and a Lyapunov theory based MLNN algorithm on three benchmark problems which are XOR, 3-bit parity, and 8-3 encoder. The results are compared in terms of number of learning iterations and computational time required for a specified convergence rate. The results clearly indicate that the proposed algorithm is much faster in convergence than other three algorithms. The proposed algorithm is also comparatively tested on a real iris image database for multiple-input and multiple-output classification problem and the effect of adaptation gain rate for faster convergence and higher performance is verified.
dc.description.sponsorshipNigde University [FEB-2010/32]; Scientific Research Project Unit [FEB-2010/32]
dc.description.sponsorshipThis study has partially been supported by Nigde University, The Scientific Research Project Unit with the project number of FEB-2010/32. We also would like to thank to the authorities of Multimedia University MMU1 Iris Image Database.
dc.identifier.doi10.14311/NNW.2014.24.035
dc.identifier.endpage636
dc.identifier.issn1210-0552
dc.identifier.issue6
dc.identifier.scopus2-s2.0-84920713431
dc.identifier.scopusqualityQ4
dc.identifier.startpage619
dc.identifier.urihttps://dx.doi.org/10.14311/NNW.2014.24.035
dc.identifier.urihttps://hdl.handle.net/11480/4221
dc.identifier.volume24
dc.identifier.wosWOS:000348408100004
dc.identifier.wosqualityQ4
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthor[0-Belirlenecek]
dc.language.isoen
dc.publisherACAD SCIENCES CZECH REPUBLIC, INST COMPUTER SCIENCE
dc.relation.ispartofNEURAL NETWORK WORLD
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectLyapunov stability theory
dc.subjectmultilayer neural network
dc.subjectLagrange multiplier theory
dc.subjectadaptive learning
dc.titleLYAPUNOV THEORY BASED ADAPTIVE LEARNING ALGORITHM FOR MULTILAYER NEURAL NETWORKS
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu