Comparison of Activation Functions in the KarciFANN Method

Basit Öğe Kaydı
dc.contributor.authorKarakurt, Meral
dc.contributor.authorSaygili, Hulya
dc.contributor.authorKarci, Ali
dc.date.accessioned2026-04-04T13:18:59Z
dc.date.available2026-04-04T13:18:59Z
dc.date.issued2024
dc.departmentİnönü Üniversitesi
dc.description8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024 -- 21 September 2024 through 22 September 2024 -- Malatya -- 203423
dc.description.abstractThe lack of a certain standard in modeling Artificial Neural Networks (ANNs) sometimes provides successful results while sometimes it causes unsuccessful results depending on the changes in the selected hyper parameters. The optimization method is a hyper parameter that significantly affects the performance of ANNs. If the learning coefficient parameter used in the SGD optimization method, which is a fixed number, is chosen too small, the solution takes a long time; if it is chosen too large, it causes problems such as getting stuck in local minima and moving away from the solution. In the Karci Fractional Neural Network (KarciFANN) method proposed in this article, the learning of the network is performed by using the fractional derivative instead of the learning coefficient parameter. Thanks to the KarciFANN method, the weights are updated with a fractional derivative that changes according to the value of the error function obtained at each iteration and external intervention to the network is minimized. Activation function is another hyperparameter that affects the performance of ANNs. Activation function determines whether the output value of a neuron will be produced or not, that is, whether the neuron will be active or not. In this study, Gina_Prior2 data set was classified using KarciFANN method using sigmoid, hyperbolic tangent (tanh) and hyperbolic tangent sigmoid (tansig) activation functions and the effects of these activation functions on performance were compared. As a result of the experiments performed on the designed model, it was seen that the most successful activation function was the sigmoid function, which produced accuracy values over 99%. © 2024 IEEE.
dc.identifier.doi10.1109/IDAP64064.2024.10711149
dc.identifier.isbn979-833153149-2
dc.identifier.scopus2-s2.0-85207966815
dc.identifier.scopusqualityN/A
dc.identifier.urihttps://doi.org/10.1109/IDAP64064.2024.10711149
dc.identifier.urihttps://hdl.handle.net/11616/108063
dc.indekslendigikaynakScopus
dc.language.isotr
dc.publisherInstitute of Electrical and Electronics Engineers Inc.
dc.relation.ispartof8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.snmzKA_Scopus_20250329
dc.subjectactivation functions
dc.subjectartificial neural networks
dc.subjectKarciFANN
dc.subjectsigmoid
dc.subjecttanh
dc.subjecttansig
dc.titleComparison of Activation Functions in the KarciFANN Method
dc.title.alternativeKarciFANN Y nteminde Aktivasyon Fonksiyonlarinin Karsilastirilmasi]
dc.typeConference Object

Dosyalar

Koleksiyon

Scopus İndeksli Yayınlar Koleksiyonu