| RBF神经网络的一种鲁棒学习算法 |
| |
| 引用本文： | 刘妹琴,廖晓昕.RBF神经网络的一种鲁棒学习算法[J].华中科技大学学报(自然科学版),2000,28(2):8-10. |
| |
| 作者姓名： | 刘妹琴 廖晓昕 |
| |
| 作者单位： | 华中理工大学控制科学与工程系 |
| |
| 基金项目： | 国家自然科学基金资助项目 !( 69874 0 1 6) |
| |
| 摘 要： | 用定标鲁棒代价函数代替传统的二次型指标 ,并结合改进的遗传算法 ,搜索近最优径向基函数神经网络 ( RBFNN)的结构和参数 .实验结果表明该训练方法比其他方法具有更强的鲁棒性 ,可提高 RBFNN的泛化能力 ,自动消除训练数据中的噪声 ,再现训练数据中的潜在规律 .
|
| 关 键 词： | 径向基函数神经网络 定标鲁棒代价函数 改进遗传算法 |
| 修稿时间： | 1999-09-21 |
A Robust Learning Algorithm for RBF Neural Networks |
| |
| Liu Meiqin,Liao Xiaoxin.A Robust Learning Algorithm for RBF Neural Networks[J].JOURNAL OF HUAZHONG UNIVERSITY OF SCIENCE AND TECHNOLOGY.NATURE SCIENCE,2000,28(2):8-10. |
| |
| Authors: | Liu Meiqin Liao Xiaoxin |
| |
| Institution: | Liu Meiqin Liao Xiaoxin |
| |
| Abstract: | The near optimal structures and parameters of the radial basis function neural networks (RBFNNs) are found by replacing the quadratic loss function with a scaled robust loss function, and also incorporating with improved genetic algorithm. The experimental results show that the learning algorithm proposed is of stronger robustness than other ones, and the generalization ability of the RBFNNs would be improved. The noise mixed in the training data would be eliminated automatically, while the underlying trend in the training data would reappear. |
| |
| Keywords: | radial basis function neural network scaled robust loss function improved genetic algorithm |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
