Effect on model performance of regularization methods
Yükleniyor...
Tarih
2021
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Dicle Üniversitesi Mühendislik Fakültesi
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Artificial 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.
Açıklama
Anahtar Kelimeler
Overfitting, Machine learning, Regularization
Kaynak
Dicle Üniversitesi Mühendislik Fakültesi Mühendislik Dergisi
WoS Q Değeri
Scopus Q Değeri
Cilt
12
Sayı
5
Künye
Budak, 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.
