| Add-Mult型模糊神经网络 |
| |
| 引用本文： | 翟东海,靳蕃. Add-Mult型模糊神经网络[J]. 计算机工程, 2003, 29(21): 141-143,148 |
| |
| 作者姓名： | 翟东海 靳蕃 |
| |
| 作者单位： | 西南交通大学计算机与通信工程学院,成都,610031 |
| |
| 摘 要： | 提出了一种Add-Mult型模糊神经网络模型(AMFNN)，给出了该模型的结构。根据梯度下降算法，给出了AMFNN模糊神经网络的误差反传学习算法。与6种极具代表性的模糊推理方法进行比较的结果表明，AMFNN模糊神经网络模型具有推理精度高、适用范围广、泛化能力强以及实现容易等特点，因而具有广阔的应用前景。
|
| 关 键 词： | 模糊推理 Add-Mult模糊神经网络 模糊规则获取 |
| 文章编号： | 1000-3428(2003)21-0141-03 |
Add-Mult Fuzzy Neural Network |
| |
| ZHAI Donghai,JIN Fan. Add-Mult Fuzzy Neural Network[J]. Computer Engineering, 2003, 29(21): 141-143,148 |
| |
| Authors: | ZHAI Donghai JIN Fan |
| |
| Abstract: | This paper presents a model of Add-Mult fuzzy neural network (AMFNN ) and the models architecture as well. Error back propagation algorithm for AMFN N is presented according to the gradient descent method. The result compared wit h six representative fuzzy inference methods shows that AMFNN has high reasoning precision, wide application scope, strong generalization capability and easy re alization characteristics. Consequently, AMFNN has vast application prospect. |
| |
| Keywords: | Fuzzy inference Add-Mult fuzzy neural network Fuzzy rules acquisi tion |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
