中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Research on multi-degree-of-freedom neurons with weighted graphs

文献类型:期刊论文

作者Wang, Shoujue; Liu, Singsing; Cao, Wenming
刊名Advances in neural networks - isnn 2006, pt 1
出版日期2006
卷号3971页码:669-675
ISSN号0302-9743
通讯作者Wang, shoujue(sstar2002@sina.com)
英文摘要In this paper, we redefine the sample points set in the feature space from the point of view of weighted graph and propose a new covering model - multi-degree-of-freedorn neurons (mdfn). base on this model, we describe a geometric learning algorithm with 3-degree-of-freedom neurons. it identifies the sample points secs topological character in the feature space, which is different from the traditional "separation" method. experiment results demonstrates the general superiority of this algorithm over the traditional pca+nn algorithm in terms of efficiency and accuracy.
WOS关键词BIOMIMETIC PATTERN-RECOGNITION
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods
语种英语
WOS记录号WOS:000238112000098
出版者SPRINGER-VERLAG BERLIN
URI标识http://www.irgrid.ac.cn/handle/1471x/2426794
专题半导体研究所
通讯作者Wang, Shoujue
作者单位1.Chinese Acad Sci, Inst Semicond, Artificial Neural Networks Lab, Beijing 100083, Peoples R China
2.Zhejiang Univ Technol, Informat Engn Coll, Inst Intelligent Informat Syst, Hangzhou 310032, Peoples R China
推荐引用方式
GB/T 7714
Wang, Shoujue,Liu, Singsing,Cao, Wenming. Research on multi-degree-of-freedom neurons with weighted graphs[J]. Advances in neural networks - isnn 2006, pt 1,2006,3971:669-675.
APA Wang, Shoujue,Liu, Singsing,&Cao, Wenming.(2006).Research on multi-degree-of-freedom neurons with weighted graphs.Advances in neural networks - isnn 2006, pt 1,3971,669-675.
MLA Wang, Shoujue,et al."Research on multi-degree-of-freedom neurons with weighted graphs".Advances in neural networks - isnn 2006, pt 1 3971(2006):669-675.

入库方式: iSwitch采集

来源:半导体研究所

浏览0
下载0
收藏0
其他版本

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。