An Improved Genetic Algorithm and Its Application in Artificial Neural Network Training

An improved genetic algorithm is proposed in which a diffusing operator is designed. Gaussian mutation method is applied in diffusing operator and its task is mainly to perform local search. Connection weights of an artificial neural network are trained on standard XOR problem by using the proposed genetic algorithm. The results show that the proposed genetic algorithm can perform both global search and local search efficiently, therefore, it can be used to train artificial neural networks alone rather than incorporate other local search algorithms, such as BP to improve local search of training algorithm, so the proposed genetic algorithm is significant to simplify training algorithm of artificial neural networks and improve training efficiency