| 一种模块化神经网络结构用于模式识别 |
| |
| 引用本文： | 王成,秦江敏,严振华. 一种模块化神经网络结构用于模式识别[J]. 计算机工程与应用, 2002, 38(5): 83-85 |
| |
| 作者姓名： | 王成 秦江敏 严振华 |
| |
| 作者单位： | 空军雷达学院研究生队,武汉430010;空军雷达学院信息工程系,武汉430010;空军雷达学院基础部,武汉430019 |
| |
| 摘 要： | 在模式识别中,通常直接用神经网络来处理复杂的多类分类问题,其识别的误判率较大。该文基于任务分解与模块整合的思想,提出了一个模块化Kohonen神经网络(KTD)结构用于模式分类,给出了其学习方法并做了模拟仿真,模拟仿真表明KTD能够获得较高的识别率且误判率较小。
|
| 关 键 词： | 任务分解 Kohonen神经网络 模式识别 |
| 文章编号： | 1002-8331-(2002)05-0083-03 |
| 修稿时间： | 2000-12-01 |
A Kind of Modular Neural Network Structure for Pattern Recognition |
| |
| Wang Cheng Qin Jiangmin Yan Zhenhua. A Kind of Modular Neural Network Structure for Pattern Recognition[J]. Computer Engineering and Applications, 2002, 38(5): 83-85 |
| |
| Authors: | Wang Cheng Qin Jiangmin Yan Zhenhua |
| |
| Affiliation: | Wang Cheng 1 Qin Jiangmin 2 Yan Zhenhua 31 |
| |
| Abstract: | Usually,neural network is used directly for solving complicated and multiple-classify problems in pattern recognition.But this method brings higher misclassifation rate.This paper proposes a new modular Kohonen neural.network based on task decomposition and module combination for pattern recognition.It also give s the principle.Finally the paper performs simulation and the result of simulation showes that KTD has better recognition. |
| |
| Keywords: | Task decomposition(TD) Kohonen neural network Pattern recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
