Levenberg–Marquardt multi-classification using hinge loss function

Incorporating higher-order optimization functions, such as Levenberg–Marquardt (LM) have revealed better generalizable solutions for deep learning problems. However, these higher-order optimization functions suffer from very large processing time and training complexity especially as training datase...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neural networks 2021-11, Vol.143 (C), p.564-571
Hauptverfasser:	Ozyildirim, Buse Melis, Kiran, Mariam
Format:	Artikel
Sprache:	eng
Schlagworte:	Classification Hinge loss Levenberg–Marquardt Loss functions Neural networks
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!