Presentation | 1998/12/18 Support Vector Machine with Variable Kernel Functions Koji Tsuda, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The support vector machine is formulated based on a positive-definite symmetric kernel function. So, a variable kernel function, whose parameters change with regard to the central position, cannot be incorporated into SVM, because it is an asymmetric function. In this paper, we generalize SVM so that it can be applied to a kernel function which is not positive definite or symmetric. In the 3D object recognition experiment, the generalized SVM with variable kernels performed better than the conventional SVM. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Pattern recognition / Variable kernel functions / Support vector machine / Generalized SVM |
Paper # | PRMU98-175 |
Date of Issue |
Conference Information | |
Committee | PRMU |
---|---|
Conference Date | 1998/12/18(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) | Support Vector Machine with Variable Kernel Functions |
Sub Title (in English) | |
Keyword(1) | Pattern recognition |
Keyword(2) | Variable kernel functions |
Keyword(3) | Support vector machine |
Keyword(4) | Generalized SVM |
1st Author's Name | Koji Tsuda |
1st Author's Affiliation | Machine Understanding Division, Electrotechnical Laboratory() |
Date | 1998/12/18 |
Paper # | PRMU98-175 |
Volume (vol) | vol.98 |
Number (no) | 490 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |