Title :
Genetic algorithms enhanced Kohonen´s neural networks
Author :
Huang, Shyh-Jier ; Hung, Chuan-Chang
Author_Institution :
Dept. of Electr. Eng., Kaohsiung Polytech. Inst., Taiwan
Abstract :
A new approach of using genetic algorithms to improve the learning characteristics of Kohonen´s neural networks is proposed in this paper. In the proposed scheme, genetic algorithms are applied to decide initial weights in the Kohonen´s classifiers. The competitive learning is then applied to train neural networks. The proposed method was tested on the power system static security assessment and travelling salesperson problems. The results were very promising
Keywords :
genetic algorithms; power system security; self-organising feature maps; travelling salesman problems; unsupervised learning; Kohonen´s classifiers; Kohonen´s neural networks; competitive learning; genetic algorithms; initial weights; learning characteristics; power system static security assessment; travelling salesperson problems; Application software; Computer networks; Genetic algorithms; Neural network hardware; Neural networks; Neurons; Power system security; Software algorithms; System testing; Unsupervised learning;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.487503
