Effect on model performance of regularization methods

Basit Öğe Kaydı
dc.authorid0000-0002-8470-4579en_US
dc.authorid0000-0002-3769-0071en_US
dc.authorid0000-0003-4585-4168en_US
dc.contributor.authorBudak, Cafer
dc.contributor.authorMençik, Vasfiye
dc.contributor.authorAsker, Mehmet Emin
dc.date.accessioned2022-01-28T12:56:04Z
dc.date.available2022-01-28T12:56:04Z
dc.date.issued2021en_US
dc.departmentDicle Üniversitesi, Mühendislik Fakültesi, Elektrik Elektronik Mühendisliği Bölümüen_US
dc.description.abstractArtificial Neural Networks with numerous parameters are tremendously powerful machine learning systems. Nonetheless, overfitting is a crucial problem in such networks. Maximizing the model accuracy and minimizing the amount of loss is significant in reducing in-class differences and maintaining sensitivity to these differences. In this study, the effects of overfitting for different model architectures with the Wine dataset were investigated by Dropout, AlfaDropout, GausianDropout, Batch normalization, Layer normalization, Activity normalization, L1 and L2 regularization methods and the change in loss function the combination with these methods. Combinations that performed well were examined on different datasets using the same model. The binary cross-entropy loss function was used as a performance measurement metric. According to the results, the Layer and Activity regularization combination showed better training and testing performance compared to other combinations.en_US
dc.identifier.citationBudak, C., Mençik, V. ve Asker, M. E. (2021). Effect on model performance of regularization methods. Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi, 12(5), 757-765.en_US
dc.identifier.doi10.24012/dumf.1051352
dc.identifier.endpage765en_US
dc.identifier.issn1309-8640
dc.identifier.issn2146-4391
dc.identifier.issue5en_US
dc.identifier.startpage757en_US
dc.identifier.trdizinid498862
dc.identifier.urihttps://dergipark.org.tr/tr/download/article-file/2167595
dc.identifier.urihttps://hdl.handle.net/11468/9117
dc.identifier.urihttps://search.trdizin.gov.tr/yayin/detay/498862
dc.identifier.volume12en_US
dc.indekslendigikaynakTR-Dizin
dc.institutionauthorBudak, Cafer
dc.institutionauthorMençik, Vasfiye
dc.institutionauthorAsker, Mehmet Emin
dc.language.isoenen_US
dc.publisherDicle Üniversitesi Mühendislik Fakültesien_US
dc.relation.ispartofDicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi
dc.relation.publicationcategoryMakale - Ulusal Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectOverfittingen_US
dc.subjectMachine learningen_US
dc.subjectRegularizationen_US
dc.titleEffect on model performance of regularization methodsen_US
dc.titleEffect on model performance of regularization methods
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
Effect on model performance of regularization methods.pdf
Boyut:
788.32 KB
Biçim:
Adobe Portable Document Format
Açıklama:
Makale Dosyası
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

Dicle Üniversitesi Mühendislik Fakültesi Dergisi
TR-Dizin İndeksli Yayınlar Koleksiyonu