| 引用本文: | 韩 敏,席剑辉,程 磊.RBPN在模式识别研究中的应用[J].控制理论与应用,2002,19(6):940~944.[点击复制] |
| HAN Min,XI Jian-hui,CHENG Lei.Applications of RBPN for pattern recognition[J].Control Theory and Technology,2002,19(6):940~944.[点击复制] |
|
| RBPN在模式识别研究中的应用 |
| Applications of RBPN for pattern recognition |
| 摘要点击 2850 全文点击 1480 投稿时间：2001-09-13 修订日期：2002-06-14 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/j.issn.1000-8152.2002.6.026 |
| 2002,19(6):940-944 |
| 中文关键词 神经网络 模式识别 输入输出聚类 径向基感知器网络 建筑材料 |
| 英文关键词 artificial neural network pattern recognition IOC RBPN civil building materials |
| 基金项目 国家自然科学基金(50139020)重点项目资助. |
|
| 中文摘要 |
| 基于RBF(radialbasisfunction)网络和感知器 (perceptron)网络建立起一种新型四层前向神经网络———径向基感知器网络 (RBPN, radialbasisperceptronnetwork). 该网络主要有以下特点 :1)网络结构上, 两层隐层选择性连接 ;2 )学习规则上, 采用同时考虑输入输出样本信息的IOC(input outputclustering)聚类方法且聚类中心的形状参数σ自适应变化. 对材料成分分析领域的仿真结果表明, 该网络可成功地包含材料成分的构成信息, |
| 英文摘要 |
| Based on radial basis function neural network (RBFN) and perceptron neural network, this paper built a new four-layer feed-forward neural network named radial basis perceptron network (RBPN). This network can be summarized as follows: 1) It is selective connection between the units of two hidden layers; 2) During learning procedure, RBPN adopts input-output clustering (IOC) method, and the appearance parameter \$σ\$ of centers is self-adjustable. This is illustrated using an example taken from applications for component analysis of civil building materials. Simulation shows that RBPN can be used to predict the components of civil building materials successfully and gets good generalization ability. |