| 一种新型的广义RBF神经网络及其训练方法 |
| |
| 引用本文： | 党开放,杨利彪,林廷圻.一种新型的广义RBF神经网络及其训练方法[J].计算技术与自动化,2007,26(1):9-13. |
| |
| 作者姓名： | 党开放 杨利彪 林廷圻 |
| |
| 作者单位： | 1. 北京化工大学,机电工程学院,北京,100029
2. 西安交通大学,机械工程学院,陕西,西安,710049 |
| |
| 摘 要： | 提出一种新型的广义RBF神经网络模型,将径向基输出权值改为权函数,采用高次函数取代线性加权.给出网络学习方法,并通过仿真分析研究隐单元宽度、权函数幂次等参数的选取对网络逼近精度以及训练时间的影响.结果表明,和传统的RBF神经网络相比,该网络具有良好的逼近能力和较快的计算速度,在系统辨识和控制中具有广阔的应用前景.
|
| 关 键 词： | RBF神经网络 训练方法 函数逼近 神经网络 训练方法 Training Method RBF Neural Network General 前景 应用 控制 系统辨识 计算速度 逼近能力 结果 影响 训练时间 逼近精度 选取 参数 幂次 宽度 隐单元 |
| 文章编号： | 1003-6199（2007）01-0009-05 |
| 收稿时间： | 2006-04-29 |
| 修稿时间： | 2006-04-29 |
A New Type of General RBF Neural Network and Its Training Method |
| |
| DANG Kai-fang,YANG Li-biao,LIN Ting-qi.A New Type of General RBF Neural Network and Its Training Method[J].Computing Technology and Automation,2007,26(1):9-13. |
| |
| Authors: | DANG Kai-fang YANG Li-biao LIN Ting-qi |
| |
| Abstract: | A new type of general RBF neural network model, which replaces weight of outer layer with weight function, i.e. replaces linear weight with high order function, is proposed. Network training method is brought forward. Parameters selection such as hide layer width and power of weight function, which have effect on approximation precision and training time of the network, are investigated through simulation. The results indicate the general RBF network has better approximation ability and faster calculation speed than traditional RBF neural network , which promotes a good prospect in the field of system identification and control. |
| |
| Keywords: | RBF neural network training method function approximation |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
