Karcı fractional artificial neural networks (KarcıFANN): anew artificial neural networks model without learning rate and its problems

Basit Öğe Kaydı
dc.contributor.authorKarakurt, Meral
dc.contributor.authorSaygili, Hulya
dc.contributor.authorKarci, Ali
dc.date.accessioned2026-04-04T13:30:41Z
dc.date.available2026-04-04T13:30:41Z
dc.date.issued2025
dc.departmentİnönü Üniversitesi
dc.description.abstractThe learning rate parameter used in classical artificial neural networks (ANNs) designed with stochastic gradient descent causes problems such as failure to learn, getting stuck in local minima, memorization, and long training times (divergence problem). To address these issues, this paper proposes a novel ANN method that uses a fractional derivative instead of Newton's derivative. This method is referred to as Karc & imath; fractional ANN (Karc & imath;FANN). In classical ANNs, the weight update is done by assigning the same constant value to the learning rate in each iteration or for a set number of iterations. In contrast, in Karc & imath;FANNs, the weight update process is carried out by calculating the fractional derivative based on the error value in each iteration. Thus, in Karc & imath;FANN, external intervention in the network is minimized compared to that of classical ANNs. Karc & imath;FANN and classical ANN methods were compared for the classification of MNIST and fashion-MNIST datasets. The Karc & imath;FANN method produces successful results for fractional derivative orders between 0.8 and 1.8. The highest accuracy values obtained in the classification of the MNIST dataset were 99.39% for Karc & imath;FANN and 99.43% for classical ANN in the training phase, and 96.76% for Karc & imath;FANN and 96.72% for classical ANN in the validation phase. The highest accuracy values obtained in the classification of the Fashion-MNIST dataset were 98.10% for Karc & imath;FANN and 98.11% for classical ANN in the training phase, and 88.56% for Karc & imath;FANN and 88.54% for classical ANN in the validation phase. The experimental studies show that Karc & imath;FANN is a competitive alternative to classical ANN. Karc & imath;FANN learns faster than classical ANN and eliminates the learning coefficient problem. Additionally, it is seen that the Karc & imath;FANN method is more successful in global modeling. However, achieving the optimal model in Karc & imath;FANN depends on the dataset and hyperparameters.
dc.identifier.doi10.55730/1300-0632.4125
dc.identifier.issn1300-0632
dc.identifier.issn1303-6203
dc.identifier.issue3
dc.identifier.scopus2-s2.0-105007765806
dc.identifier.scopusqualityQ2
dc.identifier.trdizinid1333441
dc.identifier.urihttps://doi.org/10.55730/1300-0632.4125
dc.identifier.urihttps://search.trdizin.gov.tr/tr/yayin/detay/1333441
dc.identifier.urihttps://hdl.handle.net/11616/108309
dc.identifier.volume33
dc.identifier.wosWOS:001521286100002
dc.identifier.wosqualityQ3
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.indekslendigikaynakTR-Dizin
dc.language.isoen
dc.publisherTubitak Scientific & Technological Research Council Turkey
dc.relation.ispartofTurkish Journal of Electrical Engineering and Computer Sciences
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.snmzKA_WOS_20250329
dc.subjectArtificial neural network
dc.subjectclassification
dc.subjectlearning rate
dc.subjectKarc & imath
dc.subjectfractional derivative
dc.subjectKarc & imath
dc.subjectfractional artificial neural network
dc.titleKarcı fractional artificial neural networks (KarcıFANN): anew artificial neural networks model without learning rate and its problems
dc.typeArticle

Dosyalar

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
TR-Dizin İndeksli Yayınlar Koleksiyonu