Research on multi-degree-of-freedom neurons with weighted graphs

SEMI OpenIR > 中国科学院半导体研究所（2009年前）

	Research on multi-degree-of-freedom neurons with weighted graphs
	Wang SJ (Wang Shoujue); Liu SS (Liu Singsing); Cao WM (Cao Wenming); Wang, SJ, Chinese Acad Sci, Inst Semicond, Artificial Neural Networks Lab, POB 912, Beijing 100083, Peoples R China. 电子邮箱地址: sstar2002@sina.com
	2006
会议名称	3rd International Symposium on Neural Networks (ISSN 2006)
会议录名称	ADVANCES IN NEURAL NETWORKS - ISNN 2006丛书标题: LECTURE NOTES IN COMPUTER SCIENCE
页码	PT 1 3971: 669-675 Part 1
会议日期	MAY 28-31, 2006
会议地点	Chengdu, PEOPLES R CHINA
出版地	HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY
出版者	SPRINGER-VERLAG BERLIN
ISSN	0302-9743
ISBN	3-540-34439-X
部门归属	chinese acad sci, inst semicond, artificial neural networks lab, beijing 100083, peoples r china; zhejiang univ technol, informat engn coll, inst intelligent informat syst, hangzhou 310032, peoples r china
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.
关键词	Biomimetic Pattern-recognition
学科领域	人工智能
主办者	Univ Electr Sci & Technol China.; Chinese Univ Hong Kong.; Asia Pacific Neural Network Assembly.; European Neural Network Soc.; IEEE Circuits & Syst Soc.; IEEE Computat Intelligence Soc.; Int Neural Network Soc.; Natl Nat Sci Fdn China.; KC Wong Educ Fdn Hong Kong.
收录类别	其他
语种	英语
文献类型	会议论文
条目标识符	http://ir.semi.ac.cn/handle/172111/10016
专题	中国科学院半导体研究所（2009年前）
通讯作者	Wang, SJ, Chinese Acad Sci, Inst Semicond, Artificial Neural Networks Lab, POB 912, Beijing 100083, Peoples R China. 电子邮箱地址: sstar2002@sina.com
推荐引用方式 GB/T 7714	Wang SJ ,Liu SS ,Cao WM ,et al. Research on multi-degree-of-freedom neurons with weighted graphs[C]. HEIDELBERGER PLATZ 3, D-14197 BERLIN, GERMANY:SPRINGER-VERLAG BERLIN,2006:PT 1 3971: 669-675 Part 1.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
2391.pdf（328KB）			限制开放	--	请求全文