| 用三层网络逼近任何连续函数 |
| |
| 引用本文： | 李望超,李金艳. 用三层网络逼近任何连续函数[J]. 河北工业大学学报, 1994, 0(4) |
| |
| 作者姓名： | 李望超 李金艳 |
| |
| 摘 要： | 在神经网络基础理论中，有一个这样的问题：怎样用三层网络实现对任意连续函数的映射，本文利用Ｋｏｈｏｎｅｎ提出的Ｓｅｌｆ－ＯｒｇａｎｉｚｉｎｇＦｅａｔｕｒｅＭａｐ竞争型网络以及区域的２Ｍ－分割概念，解决了用具有有限个隐层单元的三层网络以任意精度逼近一个连续函数的问题，具体的网络结构和学习算法已给出．
|
| 关 键 词： | 神经网络，逼近，三层网络，自组织特征映射，连续函数，隐单元 |
APPROXIMATING ARBITARY CONTINUOUS FUNCTION BY USING THREE-LAYERED NETWORK |
| |
| Li Wangchao,Li Jinyan.. APPROXIMATING ARBITARY CONTINUOUS FUNCTION BY USING THREE-LAYERED NETWORK[J]. Journal of Hebei University of Technology, 1994, 0(4) |
| |
| Authors: | Li Wangchao Li Jinyan. |
| |
| Affiliation: | Li Wangchao;Li Jinyan. |
| |
| Abstract: | There is such a problem in the Neural Network basic that is how to realize an arbitary continuous function by a three-layered network.In this paper,by using the Self-Organizing Feature Map competitive network presented by Kohonen in 1981,and 2M-partition definition of domain,a new method has been discussed to solve the problem of how to approximate arbitrary continuous function defined on a hypercube by utilizing a.network with definite hidden unit and a satisfactory conclusion has been obtained.The network architecture and learning algorithm is given in detail. |
| |
| Keywords: | Neural Network Approximate Three-layered Network Self-Organizing Feature Map Continuous Function Hidden unit |
| 本文献已被 CNKI 等数据库收录！ |
