| 模糊神经网络结构动态学习算法 |
| |
| 引用本文： | 鲍其莲,张炎华,朱荣.模糊神经网络结构动态学习算法[J].上海交通大学学报,2000,34(11):1489-1491,1526. |
| |
| 作者姓名： | 鲍其莲 张炎华 朱荣 |
| |
| 作者单位： | 上海交通大学,信息检测技术及仪器系,上海,200030 |
| |
| 基金项目： | 中国船舶总公司基金资助项目!(编号 :97J4 0 .5.2 ) |
| |
| 摘 要： | 提出了一种模糊神经网络（ＦＮＮ）结构学习算法，根据输入样本动态构建ＦＮＮ的输入节点及其对应的输入隶属函数，从而实现动态确定ＦＮＮ的结构，大大减少了对初始学习本本数目的要求，提出了ＦＮＮ学习算法在实时控制中的适应能力，仿真结果表明，这一算法很好地实现了对超出初始学习样本范围的其他样本的学习。
|
| 关 键 词： | 模糊神经网络 隶属函数 结构动态学习算法 |
Dynamically Learning Algorithm for Fuzzy Neural Network Structure |
| |
| BAO Qi-lian,ZHANG Yan-hua,ZHU Rong.Dynamically Learning Algorithm for Fuzzy Neural Network Structure[J].Journal of Shanghai Jiaotong University,2000,34(11):1489-1491,1526. |
| |
| Authors: | BAO Qi-lian ZHANG Yan-hua ZHU Rong |
| |
| Abstract: | A dynamically learning method for fuzzy neural network structure was presented. The number of input fuzzy membership functions is adjusted by adding, pruning and combining the membership function knots according to the new samples. The parameters of membership functions are determined by the distance of samples. The results of simulation show that the proposed methods can learn in a satisfying accuracy with almost no requirement for the number or distribution of initial samples. |
| |
| Keywords: | fuzzy neural network(FNN) membership function structure learning |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
