| 协同神经网络聚类型学习算法 |
| |
| 引用本文： | 董火明,高隽,陈定国,陈迎春.协同神经网络聚类型学习算法[J].合肥工业大学学报(自然科学版),2002,25(4):492-495. |
| |
| 作者姓名： | 董火明 高隽 陈定国 陈迎春 |
| |
| 作者单位： | 1. 合肥工业大学,计算机与信息学院,安徽,合肥,230009
2. 安徽省公路管理,局,安徽,合肥,230011 |
| |
| 基金项目： | 国家自然科学基金资助项目 ( 6 0 175 0 11)，安徽省自然科学基金资助项目 ( 0 10 42 30 1)，教育部优秀青年教师资助计划项目 |
| |
| 摘 要： | 协同神经网络是一类全新的神经网络 ,它可以根据竞争神经网络的一般原则划分为匹配子网和竞争子网。其中 ,匹配子网的学习是协同神经网络的一个中心问题。改善匹配子网的学习效率有 2种途径 :对伴随向量求解算法的改进和原型向量选取方法的改进。文章浅析了这 2种类型的学习算法 ,着重研究了聚类算法在原型向量选取中的应用 ,并以一组交通标志图像作为识别样本 ,验证了选取原型向量 2种思路的有效性。
|
| 关 键 词： | 协同神经网络 学习算法 聚类 模式识别 |
| 文章编号： | 1003-5060(2002)04-0492-04 |
| 修稿时间： | 2002年1月15日 |
Cluster learning algorithm of synergetic neural network |
| |
| DONG Huo-ming ,GAO Jun ,CHEN Ding-guo ,CHEN Ying-chun.Cluster learning algorithm of synergetic neural network[J].Journal of Hefei University of Technology(Natural Science),2002,25(4):492-495. |
| |
| Authors: | DONG Huo-ming GAO Jun CHEN Ding-guo CHEN Ying-chun |
| |
| Institution: | DONG Huo-ming 1,GAO Jun 1,CHEN Ding-guo 1,CHEN Ying-chun 2 |
| |
| Abstract: | Synergetic neural network is a new kind of neural network. According to the theory of competitive neural network, it can be divided into two parts: the matching sub-network and the competitive sub-network. And the learning of the matching sub-network is the basic problem of synergetic neural network. There are two ways to enhance the learning efficiency of the matching sub-network: by improving the method of obtaining the adjoining vectors and by improving the method of selecting the prototype vectors. In this paper,the two solutions are discussed, and the application of cluster algorithm in selecting the prototype vectors is studied in detail. Examples prove that the presented two ideas for selecting the prototype vectors are effective in dealing with the images of a set of traffic signs. |
| |
| Keywords: | synergetic neural network learning algorithm cluster pattern recognition |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
