A new efficient training strategy for deep neural networks by hybridization of artificial bee colony and limited–memory BFGS optimization algorithms

Working up with deep learning techniques requires profound understanding of the mechanisms underlying the optimization of the internal parameters of complex structures. The major factor limiting this understanding is that there exist only a few optimization methods such as gradient descent and Limit...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neurocomputing (Amsterdam) Jg. 266; S. 506 - 526
Hauptverfasser:	Badem, Hasan, Basturk, Alper, Caliskan, Abdullah, Yuksel, Mehmet Emin
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier B.V 29.11.2017
Schlagworte:	Artificial bee colony optimization algorithm Deep learning Deep neural network Hybridization L-BFGS Stacked autoencoder network Training strategy Deep learning Deep neural network Stacked autoencoder network Artificial bee colony optimization algorithm L-BFGS Hybridization Training strategy
ISSN:	0925-2312, 1872-8286
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!