Nonlinear Component Analysis as a Kernel Eigenvalue Problem

Nonlinear Component Analysis as a Kernel Eigenvalue Problem (1996)

by Bernhard Schölkopf , Alexander Smola , Klaus-Robert Müller

Citations:

User correction supplied by mph

Datum	Value	Source
TITLE	Nonlinear Component Analysis as a Kernel Eigenvalue Problem	SVM HeaderParse 0.1
AUTHOR NAME	Bernhard Schölkopf	user correction
AUTHOR NAME	Alexander Smola	user correction
AUTHOR NAME	Klaus-Robert Müller	user correction
ABSTRACT	We describe a new method for performing a nonlinear form of Principal Component Analysis. By the use of integral operator kernel functions, we can efficiently compute principal components in high-dimensional feature spaces, related to input space by some nonlinear map; for instance the space of all possible 5-pixel products in 16\Theta16 images. We give the derivation of the method, along with a discussion of other techniques which can be made nonlinear with the kernel approach; and present first experimental results on nonlinear feature extraction for pattern recognition.	user correction
YEAR	1996	user correction
CITATIONS	3 found	ParsCit 1.0