Research on multi-degree-of-freedom neurons with weighted graphs
Data(s) |
2006
|
---|---|
Resumo |
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. |
Identificador | |
Idioma(s) |
英语 |
Fonte |
Wang SJ (Wang Shoujue); Liu SS (Liu Singsing); Cao WM (Cao Wenming) .Research on multi-degree-of-freedom neurons with weighted graphs ,ADVANCES IN NEURAL NETWORKS - ISNN 2006,2006,PT 1 3971(0):669-675 |
Palavras-Chave | #半导体物理 #BIOMIMETIC PATTERN-RECOGNITION |
Tipo |
期刊论文 |