计算机科学 ›› 2007, Vol. 34 ›› Issue (5): 171-174.

• 计算机网络与信息安全 • 上一篇    下一篇

前馈优先排序神经网络的构造算法及分析

  

  • 出版日期:2018-11-16 发布日期:2018-11-16

  • Online:2018-11-16 Published:2018-11-16

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(PONN)原理与构造算法,提出了各向同性的随机分割算法(RPA)和中心选择算法(csA),最后给出标准测试集的分类测试结果,并对其进行了分析与讨论,实验结果表明PONN构造方法优于传统前馈神经网络。

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 and analysis of architecture for PONN, and promote RPA and CSA based on isotropy in HDS. Benchmark testing sets are launched in the pager. From the result of experime

Key words: PONN, Pattern recognition, Topology space

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!