| SIMO傅里叶三角基神经网络的权值直接确定法和结构自确定算法 |
| |
| 引用本文： | 张雨浓,李钧,张智军,阮恭勤,姜孝华.SIMO傅里叶三角基神经网络的权值直接确定法和结构自确定算法[J].信息与控制,2011,40(4). |
| |
| 作者姓名： | 张雨浓 李钧 张智军 阮恭勤 姜孝华 |
| |
| 作者单位： | 中山大学信息科学与技术学院,广东广州,510006 |
| |
| 基金项目： | 教育部“新世纪优秀人才支持计划”资助项目(NCET-07-0887) |
| |
| 摘 要： | 根据傅里叶级数逼近理论,将正交三角函数系作为隐层神经元激励函数,合理选取这些激励函数的周期参数,构造单输入多输出(SIMO)傅里叶三角基神经网络模型.根据该网络的特点,推导出一种基于伪逆的权值直接确定法,从而1步计算出网络最优权值,并在此基础上设计出隐层结构自确定算法.仿真结果表明,与传统BP(反向传播)神经网络及基于最小二乘法的SIMO傅里叶神经网络模型相比,本网络模型具有更高的计算精度和更快的计算速度.
|
| 关 键 词： | SIMO傅里叶三角基神经网络 权值直接确定 隐层结构自确定 |
A Weights-Direct-Determination Method and Structure-Automatic-Determination Algorithm for SIMO Trigonometrically-Activated Fourier Neural Networks |
| |
| ZHANG Yunong,LI Jun,ZHANG Zhijun,RUAN Gongqin,JIANG Xiaohua.A Weights-Direct-Determination Method and Structure-Automatic-Determination Algorithm for SIMO Trigonometrically-Activated Fourier Neural Networks[J].Information and Control,2011,40(4). |
| |
| Authors: | ZHANG Yunong LI Jun ZHANG Zhijun RUAN Gongqin JIANG Xiaohua |
| |
| Affiliation: | ZHANG Yunong,LI Jun,ZHANG Zhijun,RUAN Gongqin,JIANG Xiaohua(School of Information Science and Technology,Sun Yat-sen University,Guangzhou 510006,China) |
| |
| Abstract: | According to Fourier series approximation theory,a single-input multiple-output(SIMO) trigonometrically-activated Fourier neural network model is constructed by setting the hidden-layer neuron activation function as orthogonal trigonometric function series and selecting the periodical parameter of these activation functions properly.In light of the characteristics of the presented network,a pseudo-inverse based weights-direct-determination method is derived to determine the optimal weights of the network wi... |
| |
| Keywords: | SIMO(single input multiple output) trigonometrically-activated Fourier neural network weight direct deter-mination hidden-layer structure automatic determination |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
