Please use this identifier to cite or link to this item: https://hdl.handle.net/20.500.11851/10999
Full metadata record
DC FieldValueLanguage
dc.contributor.authorEfe, M.O.-
dc.contributor.authorKurkcu, B.-
dc.contributor.authorKasnakoglu, C.-
dc.contributor.authorMohamed, Z.-
dc.contributor.authorLiu, Z.-
dc.date.accessioned2024-01-21T09:24:31Z-
dc.date.available2024-01-21T09:24:31Z-
dc.date.issued2023-
dc.identifier.issn1549-7747-
dc.identifier.urihttps://doi.org/10.1109/TCSII.2023.3335140-
dc.identifier.urihttps://hdl.handle.net/20.500.11851/10999-
dc.description.abstractLevenberg-Marquardt (LM) algorithm is a powerful approach to optimize the parameters of a neural network (NN). Given a training dataset, the algorithm synthesizes the best path toward the optimum. This paper demonstrates the use of LM optimization algorithm when there are more than one dataset and on/off type switching of NN parameters is allowed. For each dataset a pre-selected set of parameters are allowed for modification and the proposed scheme reformulates the Jacobian under the switching mechanism. The results show that a NN can store information available in different datasets by a simple modification to the original LM algorithm, which is the novelty introduced in this study. The results are verified on a regression problem. IEEEen_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_US
dc.relation.ispartofIEEE Transactions on Circuits and Systems II: Express Briefsen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectArtificial neural networks; Biological neural networks; Jacobian matrices; Levenberg-Marquardt Algorithm; Masked Neural Networks; Multiple Dataset Learning; Neurons; Optimization; Training; Tuningen_US
dc.subjectBioinformatics; DNA; Jacobian matrices; Learning algorithms; Parameter estimation; Best paths; Biological neural networks; Levenberg-Marquardt algorithm; Masked neural network; Multiple data sets; Multiple dataset learning; Neural-networks; Optimisations; Training dataset; Tuning; Neural networksen_US
dc.titleA Modified Levenberg Marquardt Algorithm for Simultaneous Learning of Multiple Datasetsen_US
dc.typeArticleen_US
dc.departmentTOBB ETÜen_US
dc.identifier.startpage1en_US
dc.identifier.endpage1en_US
dc.identifier.wosWOS:001193325900125-
dc.identifier.scopus2-s2.0-85179098143-
dc.institutionauthor…-
dc.identifier.doi10.1109/TCSII.2023.3335140-
dc.authorscopusid7004595398-
dc.authorscopusid56062372800-
dc.authorscopusid24802064500-
dc.authorscopusid58752963600-
dc.authorscopusid58752505600-
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.identifier.scopusqualityQ1-
dc.identifier.wosqualityQ2-
item.grantfulltextnone-
item.fulltextNo Fulltext-
item.openairetypeArticle-
item.languageiso639-1en-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.cerifentitytypePublications-
crisitem.author.dept02.5. 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
Show simple item record



CORE Recommender

SCOPUSTM   
Citations

4
checked on Apr 19, 2025

WEB OF SCIENCETM
Citations

2
checked on Apr 12, 2025

Page view(s)

62
checked on Apr 21, 2025

Google ScholarTM

Check




Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.