A hyper-heuristic based reinforcement-learning algorithm to train feedforward neural networks

Basit Öğe Kaydı
dc.authoridGolcuk, Ilker/0000-0002-8430-7952
dc.authorwosidGolcuk, Ilker/B-2116-2015
dc.contributor.authorÖzsoydan, Fehmi Burçin
dc.contributor.authorGölcük, İlker
dc.date.accessioned2023-03-22T19:47:19Z
dc.date.available2023-03-22T19:47:19Z
dc.date.issued2022
dc.departmentBelirleneceken_US
dc.description.abstractArtificial Neural Networks (ANNs) offer unique opportunities in numerous research fields. Due to their remarkable generalization capabilities, they have grabbed attention in solving challenging problems such as classification, function approximation, pattern recognition and image processing that can be quite complex to model mathematically in practice. One of the most vital issues regarding the ANNs is the training process. The aim at this stage is to find the optimum values of ANN parameters such as weights and biases, which indeed embed the whole information of the network. Traditional gradient-descent -based training methods include various algorithms, of which the backpropagation is one of the best-known. Such methods have been shown to exhibit outstanding results, however, they are known have two major theoretical and computational limitations, which are slow convergence speed and possible local minima issues. For this purpose, numerous stochastic search algorithms and heuristic methods have been individually used to train ANNs. However, methods, bringing diverse features of different optimiz-ers together are still lacking in the related literature. In this regard, this paper aims to develop a training algorithm operating based on a hyper-heuristic (HH) framework, which indeed resembles reinforcement learning-based machine learning algorithm. The proposed method is used to train Feed-forward Neural Networks, which are specific forms of ANNs. The proposed HH employs individual metaheuristic algo-rithms such as Particle Swarm Optimization (PSO), Differential Evolution (DE) Algorithm and Flower Pollination Algorithm (FPA) as low-level heuristics. Based on a feedback mechanism, the proposed HH learns throughout epochs and encourages or discourages the related metaheuristic. Thus, due its stochas-tic nature, HH attempts to avoid local minima, while utilizing promising regions in search space more conveniently by increasing the probability of invoking relatively more promising heuristics during train-ing. The proposed method is tested in both function approximation and classification problems, which have been adopted from UCI machine learning repository and existing literature. According to the com-prehensive experimental study and statistically verified results, which point out significant improve-ments, the developed HH based training algorithm can achieve significantly superior results to some of the compared optimizers.(c) 2022 Karabuk University. Publishing services by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).en_US
dc.identifier.doi10.1016/j.jestch.2022.101261
dc.identifier.issn2215-0986
dc.identifier.scopus2-s2.0-85138153046en_US
dc.identifier.scopusqualityQ1en_US
dc.identifier.urihttps://doi.org/10.1016/j.jestch.2022.101261
dc.identifier.urihttps://hdl.handle.net/20.500.14034/616
dc.identifier.volume35en_US
dc.identifier.wosWOS:000892452200005en_US
dc.identifier.wosqualityQ1en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherElsevier - Division Reed Elsevier India Pvt Ltden_US
dc.relation.journalEngineering Science And Technology-An International Journal-Jestechen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectArtificial neural networksen_US
dc.subjectMachine learningen_US
dc.subjectHyper -heuristicsen_US
dc.subjectParticle swarm optimizationen_US
dc.subjectFlower pollination algorithmen_US
dc.subjectDifferential evolution algorithmen_US
dc.subjectParticle Swarm Optimizationen_US
dc.subjectGenetic Algorithmen_US
dc.subjectImproved Psoen_US
dc.subjectEvolutionaryen_US
dc.subjectMetaheuristicsen_US
dc.subjectIntelligenceen_US
dc.titleA hyper-heuristic based reinforcement-learning algorithm to train feedforward neural networksen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
gölcük.pdf
Boyut:
1018.64 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam metin / Full text
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Endüstri Mühendisliği Bölümü Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu