| 改进粒子群算法在BP神经网络拟合非线性函数方面的应用 |
| |
| 引用本文： | 乔冰琴,常晓明.改进粒子群算法在BP神经网络拟合非线性函数方面的应用[J].太原理工大学学报,2012,43(5):558-563. |
| |
| 作者姓名： | 乔冰琴 常晓明 |
| |
| 作者单位： | 1. 太原理工大学计算机科学与技术学院,太原030024;山西省财政税务专科学校经济信息系,太原030024
2. 太原理工大学计算机科学与技术学院,太原,030024 |
| |
| 基金项目： | 山西省科技攻关基金资助项目(20080322008) |
| |
| 摘 要： | 为解决BP神经网络拟合非线性函数的预测结果误差较大问题,笔者将标准粒子群算法进行改进,形成基于免疫接种的粒子群算法(IPSO);然后将该算法与BP神经网络理论相结合,实现基于IPSO算法优化的BP神经网络非线性函数拟合算法。新的拟合算法首先确定BP神经网络结构,然后用IPSO算法优化初始权值和阈值,最后进行BP神经网络预测。数值实验表明,本文提出的IPSO算法提高了BP神经网络的拟合能力,减小了拟合误差,提高了拟合精度。
|
| 关 键 词： | BP神经网络 粒子群算法 函数拟合 免疫接种 |
Application of Improved PSO in Fitting Nonlinear Function by the BP Neural Network |
| |
| QIAO Bingqin
,
CHANG Xiaoming.Application of Improved PSO in Fitting Nonlinear Function by the BP Neural Network[J].Journal of Taiyuan University of Technology,2012,43(5):558-563. |
| |
| Authors: | QIAO Bingqin CHANG Xiaoming |
| |
| Institution: | 1(1.College of Computer Science and Technology,TUT,Taiyuan 030024,China; 2.Department of Economic Information,Shanxi Finance and Taxation College,Taiyuan 030024,China) |
| |
| Abstract: | The prediction error is relatively large when BP neural network fits non-linear function.To solve this problem,the standard particle swarm algorithm was improved to immunization-based particle swarm optimization(IPSO);and then this algorithm was combined with BP neural network theory to achieve a non-linear function fitting algorithm of BP neural network which was optimized by IPSO algorithm.First,new fitting algorithm determines the BP neural network structure;second,IPSO optimizes the initial weights and thresholds;and finally BP neural network predicts the output of nonlinear function.Numerical experiments show that IPSO improved the fitting capabilities and fitting accuracy and reduced the fitting error of BP neural network. |
| |
| Keywords: | BP neural network PSO function fitting Immunization |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
