A learning algorithm with a gradient normalization and a learning rate adaptation for the mini-batch type learning

The development of a high-performance optimization algorithm to solve the learning problem of the neural networks is strongly demanded with the advance of the deep learning. The learning algorithms with gradient normalization mechanisms have been investigated, and their effectiveness has been shown....

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2017 56th Annual Conference of the Society of Instrument and Control Engineers of Japan (SICE) S. 811 - 816
Hauptverfasser:	Ito, Daiki, Okamoto, Takashi, Koakutsu, Seiichi
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	The Society of Instrument and Control Engineers - SICE 01.09.2017
Schlagworte:	Biological neural networks Computational efficiency Convolutional neural networks Electronic mail Learning algorithm Machine learning Neural networks Optimization Stochastic gradient descent method Training data
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!