DocumentCode
381161
Title
The analysis of the local search efficiency of genetic neural networks and the improvement of algorithm
Author
Wen, Shaochun ; Luo, Fei ; Mo, Hongqiang ; Lu, Ting
Author_Institution
Coll. of Electron. & Inf. Eng., South China Univ. of Technol., Guangzhou, China
Volume
3
fYear
2002
fDate
2002
Firstpage
1789
Abstract
Several concepts, such as "locus fitness" and "locus influencing factors", and a coding norm of "maximizing the locus influencing factors" are proposed, based on which the local search efficiency of genetic neural networks is analyzed. To counter the problem that "locus influencing factors" are too small, we modify the algorithm by rising the probabilities of mutation and crossover to improve the optimum seeking performance.
Keywords
genetic algorithms; neural nets; search problems; crossover; genetic algorithm; genetic neural networks; local search efficiency; locus fitness; locus influencing factors; mutation; optimum seeking performance; probability; Algorithm design and analysis; Counting circuits; Educational institutions; Electronic mail; Genetic algorithms; Genetic engineering; Genetic mutations; Information analysis; Multi-layer neural network; Neural networks;
fLanguage
English
Publisher
ieee
Conference_Titel
Intelligent Control and Automation, 2002. Proceedings of the 4th World Congress on
Print_ISBN
0-7803-7268-9
Type
conf
DOI
10.1109/WCICA.2002.1021390
Filename
1021390
Link To Document