We study a pattern classification algorithm which has recently been proposed by Vapnik and coworkers. It builds on a new inductive principle which assumes that in addition to positive and negative data, a third class of data is available, termed the Universum. We assay the behavior of the algorithm by establishing links with Fisher discriminant analysis and oriented PCA, as well as with an SVM in a projected subspace (or, equivalently, with a data-dependent reduced kernel). We also provide experimental results.
| Author(s): | Sinz, FH. and Chapelle, O. and Agarwal, A. and Schölkopf, B. |
| Book Title: | Advances in neural information processing systems 20 |
| Journal: | Advances in Neural Information Processing Systems 20: 21st Annual Conference on Neural Information Processing Systems 2007 |
| Pages: | 1369-1376 |
| Year: | 2008 |
| Month: | September |
| Day: | 0 |
| Editors: | JC Platt and D Koller and Y Singer and S Roweis |
| Publisher: | Curran |
| Bibtex Type: | Conference Paper (inproceedings) |
| Address: | Red Hook, NY, USA |
| Event Name: | 21st Annual Conference on Neural Information Processing Systems (NIPS 2007) |
| Event Place: | Vancouver, BC, Canada |
| Digital: | 0 |
| Electronic Archiving: | grant_archive |
| ISBN: | 978-1-605-60352-0 |
| Language: | en |
| Organization: | Max-Planck-Gesellschaft |
| School: | Biologische Kybernetik |
| Links: | |
BibTex
@inproceedings{4709,
title = {An Analysis of Inference with the Universum},
journal = {Advances in Neural Information Processing Systems 20: 21st Annual Conference on Neural Information Processing Systems 2007},
booktitle = {Advances in neural information processing systems 20},
abstract = {We study a pattern classification algorithm which has recently been proposed by Vapnik and coworkers. It builds on a new inductive principle which assumes that in addition to positive and negative data, a third class of data is available, termed the Universum. We assay the behavior of the algorithm by establishing links with Fisher discriminant analysis and oriented PCA, as well as with an SVM in a
projected subspace (or, equivalently, with a data-dependent reduced kernel). We also provide experimental results.},
pages = {1369-1376},
editors = {JC Platt and D Koller and Y Singer and S Roweis},
publisher = {Curran},
organization = {Max-Planck-Gesellschaft},
school = {Biologische Kybernetik},
address = {Red Hook, NY, USA},
month = sep,
year = {2008},
slug = {4709},
author = {Sinz, FH. and Chapelle, O. and Agarwal, A. and Sch{\"o}lkopf, B.},
month_numeric = {9}
}