Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.11851/10999
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Efe, M.O. | - |
dc.contributor.author | Kurkcu, B. | - |
dc.contributor.author | Kasnakoglu, C. | - |
dc.contributor.author | Mohamed, Z. | - |
dc.contributor.author | Liu, Z. | - |
dc.date.accessioned | 2024-01-21T09:24:31Z | - |
dc.date.available | 2024-01-21T09:24:31Z | - |
dc.date.issued | 2023 | - |
dc.identifier.issn | 1549-7747 | - |
dc.identifier.uri | https://doi.org/10.1109/TCSII.2023.3335140 | - |
dc.identifier.uri | https://hdl.handle.net/20.500.11851/10999 | - |
dc.description.abstract | Levenberg-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. IEEE | en_US |
dc.language.iso | en | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | en_US |
dc.relation.ispartof | IEEE Transactions on Circuits and Systems II: Express Briefs | en_US |
dc.rights | info:eu-repo/semantics/closedAccess | en_US |
dc.subject | Artificial neural networks; Biological neural networks; Jacobian matrices; Levenberg-Marquardt Algorithm; Masked Neural Networks; Multiple Dataset Learning; Neurons; Optimization; Training; Tuning | en_US |
dc.subject | Bioinformatics; 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 networks | en_US |
dc.title | A Modified Levenberg Marquardt Algorithm for Simultaneous Learning of Multiple Datasets | en_US |
dc.type | Article | en_US |
dc.department | TOBB ETÜ | en_US |
dc.identifier.startpage | 1 | en_US |
dc.identifier.endpage | 1 | en_US |
dc.identifier.wos | WOS:001193325900125 | - |
dc.identifier.scopus | 2-s2.0-85179098143 | - |
dc.institutionauthor | … | - |
dc.identifier.doi | 10.1109/TCSII.2023.3335140 | - |
dc.authorscopusid | 7004595398 | - |
dc.authorscopusid | 56062372800 | - |
dc.authorscopusid | 24802064500 | - |
dc.authorscopusid | 58752963600 | - |
dc.authorscopusid | 58752505600 | - |
dc.relation.publicationcategory | Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı | en_US |
dc.identifier.scopusquality | Q1 | - |
dc.identifier.wosquality | Q2 | - |
item.fulltext | No Fulltext | - |
item.languageiso639-1 | en | - |
item.openairecristype | http://purl.org/coar/resource_type/c_18cf | - |
item.cerifentitytype | Publications | - |
item.openairetype | Article | - |
item.grantfulltext | none | - |
crisitem.author.dept | 02.5. 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 |
CORE Recommender
SCOPUSTM
Citations
3
checked on Mar 29, 2025
WEB OF SCIENCETM
Citations
2
checked on Mar 15, 2025
Page view(s)
60
checked on Mar 31, 2025
Google ScholarTM
Check
Altmetric
Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.