基于遗传算法的BP网络优化研究

Study on Back Propagation Network Optimization with Genetic Algorithms

将遗传算法（ＧＡ）用于对ＢＰ网络权重的优化，不必对其进行参数调整，减少了训练的次数和计算量，且不会造成局部最优，多数影响遗传优化效果的规律得以确定、说明ＧＡ对神经网络的优化是可行的。

Genetic algorithms (GA) is used in optimization of BP network weight value, the parameters are not adjusted, the number of times and count of calculating for training arc re duced, the best of part is not appeared, and the rule of that pa rameters influence genetic optimization effect is detemlined. This demonstrate that it is possible for GA to optimize nearal network.