Genetic algorithms enhanced Kohonen's neural networks
Shyh‐Jier Huang, Chuan-Chang Hung · 2002
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.