Pattern recognition with neural networks combined by genetic algorithm

Soft computing techniques have been recently exploited as a promising tool for achieving high performance in pattern recognition. This paper presents a hybrid method which combines neural network classifiers by genetic algori thm. Genetic algorithm gives us an effective vehicle to determine the optim al weight parameters that are multiplied by the network outputs as coeffici ents. The experimental results with the recognition problem of totally unco nstrained handwritten numerals show that the genetic algorithm produces bet ter results than the conventional methods such as averaging and Borda count . (C) 1999 Elsevier Science B.V. All rights reserved.