关键词: 数值优化, 遗传模拟退火算法, BP神经网络, 权值, 泛化性

Abstract: After studying the disadvantage of BP neural network which has low convergent speed and trap into local minima easily, an idea of designing a new hybrid neural network model which adopts the method of numerical optimization is presented. By using GeneticStimulated Annealing algorithm (GSA), expands the updated space of weight. On the basis, it makes the acquired better value as the weight of BP neural network, and the optimized BP network is not easy to trap into the local minima and has good generalization characteristic. Making the comparation GSA network with standard BP network, simulation analysis demonstrates that this network model can attain higher categories of precision. 

Key words: numerical optimization, geneticstimulated annealing algorithm, BP neural network, weight, generalization