| 一个神经网络分类器的构造 |
| |
| 引用本文： | 张建宝,赵宗涛,慈林林,陈晓峰. 一个神经网络分类器的构造[J]. 西北大学学报(自然科学版), 2000, 30(6): 473-475 |
| |
| 作者姓名： | 张建宝 赵宗涛 慈林林 陈晓峰 |
| |
| 作者单位： | [1]西北大学计算机科学系,陕西西安 [2]北京信息高技术研究所,北京 |
| |
| 摘 要： | 提出了一个构造径向基函数神经网络分类器的有效方法，利用快速聚类和统计的方法确定网络中间层及中间层到输出层间的权值，把构造的分类器用于手写体数字的分类实验，取得了比较好的结果。
|
| 关 键 词： | 径向基函数神经网络 聚类 分类器 权值 中间层 |
| 文章编号： | 1000-274 X(2000)06-0473-03 |
| 修稿时间： | 1999-01-04 |
Construction of a neural network classifier |
| |
| ZHANG Jian bao ,ZHAO Zong tao ,CI Lin lin ,CHEN Xiao feng. Construction of a neural network classifier[J]. Journal of Northwest University(Natural Science Edition), 2000, 30(6): 473-475 |
| |
| Authors: | ZHANG Jian bao ZHAO Zong tao CI Lin lin CHEN Xiao feng |
| |
| Affiliation: | ZHANG Jian bao 1,ZHAO Zong tao 1,CI Lin lin 2,CHEN Xiao feng 2 |
| |
| Abstract: | Radial basis function neural network providesa technique for approximating arbitrary nonlinear function mappings between nultidimensional spaces. Here a method is introduced to construct a RBFNN classfier by a fast clustering algorithm and the optimal weights are computed between the middle layer and output layer statistically.The method is proposed to construct an RBFNN classifier for handwritten digit recognition. The experiment showed that the method could construct a classifier quickly and the performance of the classifier was better than others. |
| |
| Keywords: | radial basis function neural network clustering linear discriminant handwritten digit recognition |
| 本文献已被 CNKI 维普 等数据库收录！ |
