优先排序覆盖神经网络原理及分析

计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (14): 64-65.

优先排序覆盖神经网络原理及分析

朱世交张南华王守觉

上海同济大学电子与信息工程学院同济大学计算机系北京912信箱中国科学院半导体研究所神经网络组

收稿日期:2006-06-13 修回日期:1900-01-01 出版日期:2007-05-10 发布日期:2007-05-10
通讯作者: 朱世交

Principles and Analysis of Priority Ordered covered Neural Network

Shijiao zhu

Received:2006-06-13 Revised:1900-01-01 Online:2007-05-10 Published:2007-05-10
Contact: Shijiao zhu

摘要/Abstract

摘要： 本文从高维空间特征点覆盖的角度，讨论了优先度排序神经网络空间覆盖理论，从理论上阐明了运用神经网络构造方法实现空间特征覆盖的意义，最后给出了两维螺旋线识别的测试用例。

关键词: 优先排序网络模式识别拓扑空间

Abstract: From the view-point of coverage in the high-dimension space (HDS), we discuss the theory of priority ordered Neural Network(PONN) and its meaning of the PONN in HDS. In the later chapter, we give a case of tow-dimension spiral line recognition based on PONN.

Key words: Priority Neural Network , Pattern recognition, Topology space

朱世交张南华王守觉. 优先排序覆盖神经网络原理及分析[J]. 计算机工程与应用, 2007, 43(14): 64-65.

Shijiao zhu. Principles and Analysis of Priority Ordered covered Neural Network[J]. Computer Engineering and Applications, 2007, 43(14): 64-65.