Sections

Personal tools

You are here: Home → Group Rätsch → People → Gunnar Rätsch, Dr. → Publications → Invariant Feature Extraction and Classification in Kernel Spaces

Navigation

Document Actions

S Mika, G Rätsch, J Weston, B Schölkopf, A J Smola, and K Müller (2000)

Invariant Feature Extraction and Classification in Kernel Spaces

In: Proc. NIPS 12 (http://www.cs.cmu.edu//Web/Groups/NIPS/NIPS99/nips99.html), ed. by S. A. Solla and T. K. Leen and K.-R. Müller, pp. 526-532, MIT Press.

Abstract

We incorporate prior knowledge to construct nonlinear algorithms for invariant feature extraction and discrimination. Employing a unified framework in terms of a nonlinear variant of the Rayleigh coefficient, we propose non-linear generalizations of Fisher's discriminant and oriented PCA using Support Vector kernel functions. Extensive simulations show the utility of our approach.

News: Paper on taxonomy-based transfer learning for Sequence classification of has been accepted for RECOMB 2010 Dec 15, 2009; Paper on Genome-wide SNP variation analysis in rice published in PNAS. Jul 14, 2009; New release of the spliced-alignment tool QPALMA Jul 13, 2009; Postdoctoral position available Jun 24, 2009; Paper on a novel Support Vector Machine-based Gene Finding System has been accepted for publication in Genome Research Jun 23, 2009; Web-based Gene finding system mGene.web available and published in Nucleic Acids Research Jun 03, 2009; Paper on Optimized Cutting Plane Algorithm accepted by Journal of Machine Learning Research Jun 01, 2009; The Scientists writes about QPALMA in the current issue Jun 01, 2009; More news…