遗传算法优化B P神经网络的目的是通过遗传算法得到更好的网络初始权值和阈值, 其

基本思想就是用个体代表网络的初始权值和阈值、 个体值初始化的B P神经网络的预测误差作为该个体的适应度值, 通过选择、 交叉、 变异操作寻找最优个体, 即最优的B P神经网络初始权值。除了遗传算法之外, 还可以采用粒子群算法、 蚁群算法等优化B P神经网络初始权值。-Genetic algorithm to optimize BP neural network is designed by means of genetic algorithms get better network initial weights and thresholds, the basic idea is to use individual represents the network' s initial weights and thresholds, the individual values ​ ​ initialized BP neural network prediction error as the individual' s fitness value, through selection, crossover and mutation to find the optimal individual, ie the optimal BP neural network initial weights. In addition to genetic algorithms, you can also use particle swarm optimization, ant colony algorithm to optimize BP neural network initial weights.