Presentation | 2008-12-18 Laplacian Eigenmaps with Semi-Supervised Feature Selection for Pattern Classification Weiwei DU, Kiichi URAHAMA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Similarity in the Laplacian eigenmap is the Gaussian function of Euclidean distance between feature vectors. In this paper, we extend it to an anisotropic Laplacian eigenmap with a weighted Euclidean distance. Its weights are learned with the semi-supervised feature selection method by Zhao et al. on the basis of partially labeled training data. All the training data are mapped into a low-dimensional space with the Laplacian eigenmap with learned weights and every unlabeled datum is labeled with the nearest neighbor rule. A test datum is classified also with the nearest neighbor rule with the weighted Euclidean distance. Performance of the proposed method is examined with a synthetic dataset and some real data. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | semi-supervised learning / Laplacian eigenmap / multivaritae mapping / semi-supervised feature selection |
Paper # | PRMU2008-152 |
Date of Issue |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 2008/12/11(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 | Pattern Recognition and Media Understanding (PRMU) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Laplacian Eigenmaps with Semi-Supervised Feature Selection for Pattern Classification |
Sub Title (in English) | |
Keyword(1) | semi-supervised learning |
Keyword(2) | Laplacian eigenmap |
Keyword(3) | multivaritae mapping |
Keyword(4) | semi-supervised feature selection |
1st Author's Name | Weiwei DU |
1st Author's Affiliation | Kyoto Institute of Technology() |
2nd Author's Name | Kiichi URAHAMA |
2nd Author's Affiliation | Kyushu University |
Date | 2008-12-18 |
Paper # | PRMU2008-152 |
Volume (vol) | vol.108 |
Number (no) | 363 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |