| 引用本文: | 吴艳焰,皇甫堪,周良柱,等.自组织特性图形的检测理论与应用.[J].国防科技大学学报,1994,16(1):9-15.[点击复制] |
| Wu Yanyan,Huangfu Kan,Zhou Liangzhu,et al.The Detection Theory of Self-Organizing Feature Map and Its Application[J].Journal of National University of Defense Technology,1994,16(1):9-15[点击复制] |
|
| |
|
|
| 本文已被：浏览 5944次 下载 6192次 |
| 自组织特性图形的检测理论与应用 |
| 吴艳焰, 皇甫堪, 周良柱, 万建伟 |
|
(国防科技大学 电子技术系 湖南 长沙 410073)
|
| 摘要: |
| 人工神经网络模型已研究多年，己使得在信息处理领域中具有类似人的性能，本文将Kohonen自组织特征映射的学习规则进行了修改，以降低拓扑邻域边界上的模糊性，而后，用它的联想存贮功能可以实现输入统计过程的特征存贮，以达到检测的目的。本文也讨论了多维检测的数学机理，作为它的一个结果，可以得出高精度的检测性能。 |
| 关键词: 神经网络，Neural Net，目检检测，Target Detection |
| DOI： |
| 投稿日期：1993-06-15 |
| 基金项目: |
|
| The Detection Theory of Self-Organizing Feature Map and Its Application |
| Wu Yanyan, Huangfu Kan, Zhou Liangzhu, Wan Jianwei |
|
(Department of Electronic Technology，NUDT，Changsha，410073)
|
| Abstract: |
| Artificial neural net models have been studied for years in the hope of achieving human like performance in the field of information processing. In the paper the learning rule of Kohonen self-organizition feature map is modified in order to decrease the fuzziness on the edges of topological neighbours. Then with its associative memory function，we can realize the memory of the features of the input stochastic process, conseqently the detection can be performed. We also describe the mathematical mechanisms of multi-dimentional detection,as its result high-accuracy performance can be derived. |
| Keywords: neural net,target detection |
|
|
|
|
|
