Deterministic convergence of complex mini-batch gradient learning algorithm for fully complex-valued neural networks

This paper investigates the fully complex mini-batch gradient algorithm for training complex-valued neural networks. Mini-batch gradient method has been widely used in neural network training, however, its convergence analysis is usually restricted to real-valued neural networks and of probability n...

Celý popis

Podrobná bibliografia

Vydané v:	Neurocomputing (Amsterdam) Ročník 407; s. 185 - 193
Hlavní autori:	Zhang, Huisheng, Zhang, Ying, Zhu, Shuai, Xu, Dongpo
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier B.V 24.09.2020
Predmet:	Convergence Fully complex-valued neural networks Mini-batch gradient algorithm Wirtinger calculus Fully complex-valued neural networks Mini-batch gradient algorithm Wirtinger calculus Convergence
ISSN:	0925-2312, 1872-8286
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!