Presentation	1998/7/27 Subspace Method in the Hilbert Space Koji Tsuda,
PDF Download Page	PDF download Page Link
Abstract(in Japanese)	(See Japanese page)
Abstract(in English)	To improve the classification accuracy of the subspace method, it is effective to reduce the dimensionality of the intersections between the subspaces. For this purpose, the feature space should be mapped to a higher dimensional space.In this paper, the feature space is mapped implicitly to the infinite dimensional Hilbert space in the same manner as the support vector machine, and the subspace method is applied to the Hilbert space. As a result of the Hiragana recognition experiment, it is shown that the classification accuracy is better than that of the conventional subspace classifier.
Keyword(in Japanese)	(See Japanese page)
Keyword(in English)	Pattern Recognition / Subspace Method / Hilbert Space / Kernel Functions / Support Vector Machine
Paper #	NC98-36
Date of Issue

Conference Information
Committee	NC
Conference Date	1998/7/27(1days)
Place (in Japanese)	(See Japanese page)
Place (in English)
Topics (in Japanese)	(See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To	Neurocomputing (NC)
Language	JPN
Title (in Japanese)	(See Japanese page)
Sub Title (in Japanese)	(See Japanese page)
Title (in English)	Subspace Method in the Hilbert Space
Sub Title (in English)
Keyword(1)	Pattern Recognition
Keyword(2)	Subspace Method
Keyword(3)	Hilbert Space
Keyword(4)	Kernel Functions
Keyword(5)	Support Vector Machine
1st Author's Name	Koji Tsuda
1st Author's Affiliation	Machine Understanding Division, Electrotechnical Laboratory()
Date	1998/7/27
Paper #	NC98-36
Volume (vol)	vol.98
Number (no)	219
Page	pp.pp.-
#Pages	8
Date of Issue