DocumentCode
3484926
Title
SOMDS: multidimensional scaling through self organization map
Author
Asakawa, Shuichirou
Volume
5
fYear
2002
fDate
18-22 Nov. 2002
Firstpage
2579
Abstract
We propose SOMDS that is a combination of MDS (multidimensional scaling) and SOM. SOMDS is a special type of MDS that can learn locally and adaptively the structure of similarity data. SOMDS is a special type of SOM without neighborhood functions and whose inputs are similarities between objects. Convergence properties of the algorithm and some applications are presented.
Keywords
correlation theory; eigenvalues and eigenfunctions; self-organising feature maps; unsupervised learning; SOMDS online version; batch style statistical procedure; convergence properties; correlation coefficients; eigenvalue problem; maximization problem; multidimensional scaling; self organization map; similarities between objects; similarity data; Convergence; Counting circuits; Eigenvalues and eigenfunctions; Equations; Multidimensional systems; Psychology; Psychometric testing; Statistical analysis; Time measurement;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN
981-04-7524-1
Type
conf
DOI
10.1109/ICONIP.2002.1201961
Filename
1201961
Link To Document