Improving gaussian processes classification by spectral data reorganizing
Date
2008
Authors
Zhou, H.
Suter, D.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Proceedings of the 19th International Conference on Pattern Recognition (ICPR), Tampa, Florida, USA., 2008: pp.1-4
Statement of Responsibility
Hang Zhou and David Suter
Conference Name
International Conference on Pattern Recognition (19th : 2008 : Florida)
Abstract
We improve Gaussian processes (GP) classification by reorganizing the (non-stationary and anisotropic) data to better fit to the isotropic GP kernel. First, the data is partitioned into two parts: along the feature with the highest frequency bandwidth. Secondly, for each part of the data, only the spectrally homogeneous features are chosen and used (the rest discarded) for GP classification. In this way, anisotropy of the data is lessened from the frequency point of view. Tests on synthetic data as well as real datasets show that our approach is effective and outperforms Automatic Relevance Determination (ARD).