Title :
Gegenbauer orthogonal basis neural network and its weights-directdetermination method
Author :
Zhang, Ye ; Li, Wenyuan
Author_Institution :
Sch. of Inf. Sci. & Technol., Sun Yat-Sen Univ., Guangzhou, China
fDate :
11/1/2009 12:00:00 AM
Abstract :
A feedforward neural-network is proposed with hidden-layer neurons activated by Gegenbauer orthogonal functions. Compared with conventional back-propagation training algorithms, a weights-direct-determination method is proposed to determine the neural-network weights directly, which avoids a lengthy iterative-training procedure. Computer simulations further substantiate the efficacy of such a Gegenbauer orthogonal basis neural network.
Keywords :
backpropagation; feedforward neural nets; Gegenbauer orthogonal basis neural network; back-propagation training algorithms; feedforward neural-network; hidden-layer neurons; weights-direct-determination method;
Journal_Title :
Electronics Letters
DOI :
10.1049/el.2009.2735