A new learning algorithm with logarithmic performance index for complex-valued neural networks

In a fully complex-valued feed-forward network, the convergence of the Complex-valued Back Propagation (CBP) learning algorithm depends on the choice of the activation function, learning sample distribution, minimization criterion, initial weights and the learning rate. The minimization criteria use...

Celý popis

Podrobná bibliografia

Vydané v:	Neurocomputing (Amsterdam) Ročník 72; číslo 16; s. 3771 - 3781
Hlavní autori:	Savitha, R., Suresh, S., Sundararajan, N., Saratchandran, P.
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Elsevier B.V 01.10.2009
Predmet:	Fully complex-valued networks Logarithmic performance index Multi-layer perceptron Split complex network Fully complex-valued networks Logarithmic performance index Multi-layer perceptron Split complex network
ISSN:	0925-2312, 1872-8286
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!