A novel type of activation function in artificial neural networks: Trained activation function

Basit Öğe Kaydı
dc.authorid0000-0003-0710-0867en_US
dc.contributor.authorErtuğrul, Ömer Faruk
dc.date.accessioned2019-07-04T13:04:01Z
dc.date.available2019-07-04T13:04:01Z
dc.date.issued2018-03en_US
dc.departmentBatman Üniversitesi Mühendislik - Mimarlık Fakültesi Elektrik-Elektronik Mühendisliği Bölümüen_US
dc.description.abstractDetermining optimal activation function in artificial neural networks is an important issue because it is directly linked with obtained success rates. But, unfortunately, there is not any way to determine them analytically, optimal activation function is generally determined by trials or tuning. This paper addresses, a simpler and a more effective approach to determine optimal activation function. In this approach, which can be called as trained activation function, an activation function was trained for each particular neuron by linear regression. This training process was done based on the training dataset, which consists the sums of inputs of each neuron in the hidden layer and desired outputs. By this way, a different activation function was generated for each neuron in the hidden layer. This approach was employed in random weight artificial neural network (RWN) and validated by 50 benchmark datasets. Achieved success rates by RWN that used trained activation functions were higher than obtained success rates by RWN that used traditional activation functions. Obtained results showed that proposed approach is a successful, simple and an effective way to determine optimal activation function instead of trials or tuning in both randomized single and multilayer ANNs.en_US
dc.identifier.citationErtuğrul, Ö F. (2018). A novel type of activation function in artificial neural networks: Trained activation function. Neural Networks, 99, pp. 148-157. https://doi.org/10.1016/j.neunet.2018.01.007en_US
dc.identifier.endpage157en_US
dc.identifier.issn0893-6080
dc.identifier.issn1879-2782
dc.identifier.scopusqualityQ1en_US
dc.identifier.startpage148en_US
dc.identifier.urihttps://doi.org/10.1016/j.neunet.2018.01.007
dc.identifier.urihttps://hdl.handle.net/20.500.12402/2179
dc.identifier.volume99en_US
dc.identifier.wosqualityQ1en_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherElsevieren_US
dc.relation.isversionof10.1016/j.neunet.2018.01.007en_US
dc.relation.journalNeural Networksen_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.subjectActivation Functionen_US
dc.subjectArtificial Neural Networken_US
dc.subjectRandom Weight Artificial Neural Networken_US
dc.subjectTrained Activation Functionen_US
dc.titleA novel type of activation function in artificial neural networks: Trained activation functionen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
İsim:
1-s2.0-S0893608018300078-main.pdf
Boyut:
597.65 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir
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:
İndir

Koleksiyon

Mühendislik-Mimarlık Fakültesi, Elektrik-Elektronik Mühendisliği Bölümü, Makale Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu