Optimization of Neural Networks with the Criterion of Minimum Risk and Genetic Algorithms

A novel approach for optimizing feed forward neural networks is proposed in this paper, the genetic algorithms is not based on the traditional criterion of minimum square error, however its fitness function is determined by the average risk. In the evolutionaryprocedure, the method considers not only the errors between the network's outputs and the desired outputs, but also the risk caused by these errors, because the errors for different types of samples in training set may present different risks. The neural networks optimized by the proposed approach has shown the good performance on the samples both inside and outside training set. ;;;;