Two novel versions of randomized feed forward artificial neural networks: Stochastic and pruned stochastic

dc.authorid0000-0003-0710-0867en_US
dc.contributor.authorErtuğrul, Ömer Faruk
dc.date.accessioned2019-07-04T13:03:04Z
dc.date.available2019-07-04T13:03:04Z
dc.date.issued2017-11-13en_US
dc.departmentBatman Üniversitesi Mühendislik - Mimarlık Fakültesi Elektrik-Elektronik Mühendisliği Bölümüen_US
dc.description.abstractAlthough high accuracies were achieved by artificial neural network (ANN), determining the optimal number of neurons in the hidden layer and the activation function is still an open issue. In this paper, the applicability of assigning the number of neurons in the hidden layer and the activation function randomly was investigated. Based on the findings, two novel versions of randomized ANNs, which are stochastic, and pruned stochastic, were proposed to achieve a higher accuracy without any time-consuming optimization stage. The proposed approaches were evaluated and validated by the basic versions of the popular randomized ANNs [1] are the random weight neural network [2], the random vector functional links [3] and the extreme learning machine [4] methods. In the stochastic version of randomized ANNs, not only the weights and biases of the neurons in the hidden layer but also the number of neurons in the hidden layer and each activation function were assigned randomly. In pruned stochastic version of these methods, the winner networks were pruned according to a novel strategy in order to produce a faster response. Proposed approaches were validated via 60 datasets (30 classification and 30 regression datasets). Obtained accuracies and time usages showed that both versions of randomized ANNs can be employed for classification and regression.en_US
dc.identifier.citationErtuğrul, Ö F. (2017). Two novel versions of randomized feed forward artificial neural networks: Stochastic and pruned stochastic. Neural Processing Letters, 48(1), pp. 481-516. https://doi.org/10.1007/s11063-017-9752-xen_US
dc.identifier.endpage516en_US
dc.identifier.issn1370-4621
dc.identifier.issn1573-773X
dc.identifier.issue1en_US
dc.identifier.scopusqualityQ2en_US
dc.identifier.startpage481en_US
dc.identifier.urihttps://doi.org/10.1007/s11063-017-9752-x
dc.identifier.urihttps://hdl.handle.net/20.500.12402/2178
dc.identifier.volume48en_US
dc.identifier.wosqualityQ2en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherSpringer Natureen_US
dc.relation.isversionof10.1007/s11063-017-9752-xen_US
dc.relation.journalNeural Processing Lettersen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.rightsAttribution-NonCommercial-ShareAlike 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/us/*
dc.subjectExtreme Learning Machinesen_US
dc.subjectPruned Stochasticen_US
dc.subjectRandom Activation Functionen_US
dc.subjectRandom Network Structureen_US
dc.subjectRandom Vector Functional Linken_US
dc.subjectRandomized Weight Neural Networken_US
dc.subjectStochasticen_US
dc.titleTwo novel versions of randomized feed forward artificial neural networks: Stochastic and pruned stochasticen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
Ertuğrul2018_Article_TwoNovelVersionsOfRandomizedFe.pdf
Boyut:
862.72 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama: