Mika, Sebastian; Raetsch, Gunnar; Weston, Jason; Schoelkopf, Bernhard; Smola, Alexander; Mueller, Klaus-Robert
We incorporate prior knowledge to construct nonlinear algorithms for invariant feature extraction and discrimination. Employing a unified framework in terms of a nonlinearized variant of the Raylelgh coefficient, we propose nonlinear generalizations of Fisher's discriminant and oriented PCA using support vector kernel functions. Extensive simulations show the utility of our approach.
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.