| 多层前向神经网络的RLS修正训练算法 |
| |
| 引用本文： | 胡云安 吴光彬. 多层前向神经网络的RLS修正训练算法[J]. 烟台大学学报(自然科学与工程版), 1999, 12(4): 272-276 |
| |
| 作者姓名： | 胡云安 吴光彬 |
| |
| 作者单位： | 海军航空工程学院自动控制工程系!烟台264001 |
| |
| 摘 要： | 提出了一种修正的基于递推最小二乘算法的多层前向神经网络的快速学习算法，对两个系统进行了辨识，并与ＲＬＳ训练算法和标准反向传播算法进行了比较，仿真结果显示，本文提出方法的鲁棒性和有效性。
|
| 关 键 词： | 神经网络 最小二乘法 鲁棒性 多层神经网络 |
A Modified RLS Algorithm for Multilayer Feedforward Neural Networks |
| |
| Hu Yunan Wu Guangbin. A Modified RLS Algorithm for Multilayer Feedforward Neural Networks[J]. Journal of Yantai University(Natural Science and Engineering edirion), 1999, 12(4): 272-276 |
| |
| Authors: | Hu Yunan Wu Guangbin |
| |
| Abstract: | A modified learning algorithm based on the recursive least squares(RLS)method for the multilayer feedforword neural networks is proposed. The algorithm has been applied to the identifications of two systems. The simulation results demonstrate the robustness of the system and the effectiveness of the proposed method. |
| |
| Keywords: | neural network identification least square method robustness |
| 本文献已被 CNKI 维普 等数据库收录！ |
