An introduction to kernel-based learning algorithms

This paper provides an introduction to support vector machines (SVMs), kern el Fisher discriminant analysis, and kernel principal component analysis (P CA), as examples for successful kernel-based learning methods, We first giv e a short background about Vapnik-Chervonenkis (VC) theory and kernel featu re spaces and then proceed to kernel based learning in supervised and unsup ervised scenarios including practical and algorithmic considerations. We il lustrate the usefulness of kernel algorithms by finally discussing applicat ions such as optical character recognition (OCR) and DNA analysis.