| PSO粒子群算法在神经网络泛化能力中研究 |
| |
| 引用本文： | 刘军,邱晓红,汪志勇,杨鹏.PSO粒子群算法在神经网络泛化能力中研究[J].计算机工程与应用,2009,45(29):34-36. |
| |
| 作者姓名： | 刘军 邱晓红 汪志勇 杨鹏 |
| |
| 作者单位： | 1.江西师范大学 计算机学院，南昌 330022 2.江西农业大学 软件学院，南昌 330045 |
| |
| 摘 要： | 利用PSO粒子群算法对神经网络的权值和阈值，隐藏层中神经元的传递函数系数进行优化。针对网络训练效果好，而泛化能力很差的情况，将训练样本均方差和权值的平方和结合作为PSO算法的目标函数。实验表明，该方法比惯性权值PSO-BP算法和基本梯度下降法好，不但稳定性好，而且预测精度高，泛化能力得到明显加强。
|
| 关 键 词： | BP网络 PSO粒子群算法 传递函数 逼近 泛化 |
| 收稿时间： | 2008-11-12 |
| 修稿时间： | 2009-2-5
|
Research on PSO algorithm in neural network generalization |
| |
| LIU Jun,QIU Xiao-hong,WANG Zhi-yong,YANG Peng.Research on PSO algorithm in neural network generalization[J].Computer Engineering and Applications,2009,45(29):34-36. |
| |
| Authors: | LIU Jun QIU Xiao-hong WANG Zhi-yong YANG Peng |
| |
| Affiliation: | 1.College of Computer，Jiangxi Normal University，Nanchang 330022，China 2.School of Software，Jiangxi Agricultural University，Nanchang 330045，China |
| |
| Abstract: | This paper employs the PSO algorithm to update the weights，the biases and the transfer function’s coefficients of the hidden layer in the neural network.As to the phenomena of good approximation and bad generalization，the MSE of the training set and the MSW of the weights are integrated into the fitness goal.In the experiment，the GPSO-BP algorithm which optimizes the coefficients of the transfer function and has the small weights and thresholds is better than the BP algorithm and the PSO-BP algorithm in terms of the mean correct recognition and the stability. |
| |
| Keywords: | Back Propagation（BP） neural network Particle Swarm Optimization（PSO） algorithm transfer function approximation generalization |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算机工程与应用》浏览原始摘要信息 |
|
点击此处可从《计算机工程与应用》下载全文 |
