粒子群算法优化BP神经网络  

Optimization of the BP Neural Netwook with Particle Swarm Algorithm

作　　者：谭乐平[1] 文军[1] 

机构地区：[1]湖北民族学院 理学院,恩施市445000

出　　处：《湖北民族学院学报（自然科学版）》2012年第3期254-255,270,共3页Journal of Hubei Minzu University(Natural Science Edition)

基　　金：国家自然科学基金项目(60973083)

摘　　要：现实生活中绝大数系统都是非线性的,BP神经网络通过训练能否达到局部最优值、能否收敛以及训练的时间长短与初始值和阈值的选取关系密切.为此采用了具有动态惯性权重的粒子群算法对BP神经网络初始值进行优化.实验表明具有动态惯性权重的粒子群算法优化BP神经网络预测误差很小,能够跳出局部极小值,得到更优的结果.Most systemms are nonlinear in real life.Whether BP neural network could meet the local optimal value through training,whether it is comvergent and how long the training lasts are closely related to the initial value and the threshold value selected.This paper use a particle swarm algorithm with dynamic inertia weight network to optimize the initial value of the BP neural network.The experiment shows that the prediction error is very small when the particle swarm algorithm is used to optimize the BP neural network. Such an algorithm can jump out of local minimum value and get better results.

关 键 词：粒子群算法 BP神经网络 个体极值 群体极值 

分 类 号：TB114.1[理学—运筹学与控制论]