| 连续小波神经网络优化结构研究 |
| |
| 引用本文： | 孙小点,任雪梅,陈杰,陶彩霞.连续小波神经网络优化结构研究[J].系统仿真学报,2001,13(Z1):156-159. |
| |
| 作者姓名： | 孙小点 任雪梅 陈杰 陶彩霞 |
| |
| 作者单位： | 北京理工大学自动控制系, |
| |
| 基金项目： | 国家自然科学基金资助项目(69804001) |
| |
| 摘 要： | 通过仿真实验发现凭经验选取小波神经网络隐层小波基,所得结构并不最优.为此,本文将遗传算法与小波神经网络结合起来进行研究.利用遗传算法来优化小波神经网络的结构,确定小波基的个数,采用BP算法来训练小波神经网络中的伸缩因子、平移因子和连接权值.仿真结果表明,该方法能准确搜索到最优结构,是切实可行的.
|
| 关 键 词： | 遗传算法 小波神经网络 优化 梯度法 |
| 文章编号： | 1004-731X(2001)0A-0156-04 |
| 修稿时间： | 2001年5月8日 |
The Optimization to the Structure of a Continuous Wavelet Neural Network |
| |
| SUN Xiao-dian,REN Xue-mei,CHEN Jie,TAO Cai-xia.The Optimization to the Structure of a Continuous Wavelet Neural Network[J].Journal of System Simulation,2001,13(Z1):156-159. |
| |
| Authors: | SUN Xiao-dian REN Xue-mei CHEN Jie TAO Cai-xia |
| |
| Abstract: | It is shown that the wavelet network structure with hidden layer decided by experience is not the optimization. In this paper we discuss the optimization to the structure of wavelet neural networks, for which the genetic algorithm is used to determine the number of elements in hidden layer while the gradient method of BP algorithm is used to compute weighting, stretching and displacing coefficients of the continuous wavelet neural networks. The effectiveness of the proposed scheme is demonstrated by examples |
| |
| Keywords: | genetic algorithm wavelet neural network optimization gradient method |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
