Title :
A Novel Modified Genetic Algorithm for Training Wavelet Neural Networks
Author :
Li Jing ; Wang Jin-Jia ; Hou Chun-Liang ; Hong, Wen-xue ; Hong Wen-Xue
Author_Institution :
Coll. of Sci., Yanshan Univ., Qinhuangdao, China
Abstract :
Inspired by the genetic algorithm (GA) and wavelet neural networks, a novel modified GA algorithm is proposed for finding the optimal number of hidden layer as well as the networks parameters. The efficacy of the proposed algorithm in function approximation is demonstrated through theoretical analysis and experimental results.
Keywords :
function approximation; genetic algorithms; learning (artificial intelligence); neural nets; function approximation; genetic algorithm; wavelet neural network training; Approximation algorithms; Artificial neural networks; Function approximation; Gallium; Genetic algorithms; Signal processing algorithms; Training; Wavelet Neural Networks; function approximation; genetic algorithm;
Conference_Titel :
Pervasive Computing Signal Processing and Applications (PCSPA), 2010 First International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4244-8043-2
Electronic_ISBN :
978-0-7695-4180-8
DOI :
10.1109/PCSPA.2010.193
