DocumentCode :
596717
Title :
Neural network structure optimization based on improved genetic algorithm
Author :
Wei Wu
Author_Institution :
Dept. of Comput. Eng., Suzhou Vocational Univ., Suzhou, China
fYear :
2012
fDate :
18-20 Oct. 2012
Firstpage :
893
Lastpage :
895
Abstract :
For structural optimization of neural networks, i.e., the challenging problem to determine the number of hidden layers and the number of neurons, we propose a structural optimization algorithm based on an improved genetic algorithm (IGA). The proposed algorithm is then employed to approximate nonlinear function y=e-(x-1)2+e-(x+1)2 in MATLAB. Extensive simulation demonstrates that the proposed optimization algorithm is efficient, improves adaptability and generalization ability of neural networks, and holds rapid global convergence.
Keywords :
approximation theory; convergence of numerical methods; genetic algorithms; neural nets; nonlinear functions; IGA; MATLAB; approximate nonlinear function; improved genetic algorithm; neural network structure optimization; rapid global convergence; structural optimization; Approximation algorithms; Artificial neural networks; Biological neural networks; Genetic algorithms; Neurons; Optimization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Advanced Computational Intelligence (ICACI), 2012 IEEE Fifth International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4673-1743-6
Type :
conf
DOI :
10.1109/ICACI.2012.6463299
Filename :
6463299
Link To Document :
بازگشت