A Recursive Online Kernel PCA Algorithm

Author

Hasanbelliu, Erion ; Giraldo, Luis Sánchez ; Principe, José C.

Author_Institution

ECE Dept., Univ. of Florida, Gainesville, FL, USA

fYear

2010

fDate

23-26 Aug. 2010

Firstpage

169

Lastpage

172

Abstract

In this paper, we describe a new method for performing kernel principal component analysis which is online and also has a fast convergence rate. The method follows the Rayleigh quotient to obtain a fixed point update rule to extract the leading eigenvalue and eigenvector. Online deflation is used to estimate the remaining components. These operations are performed in reproducing kernel Hilbert space (RKHS) with linear order memory and computation complexity. The derivation of the method and several applications are presented.

Keywords

Hilbert spaces; computational complexity; eigenvalues and eigenfunctions; feature extraction; principal component analysis; RKHS; Rayleigh quotient; computation complexity; convergence rate; eigenvalue; eigenvector; fixed point update rule; kernel principal component analysis; linear order memory; online deflation; recursive online kernel PCA algorithm; reproducing kernel Hilbert space; Complexity theory; Convergence; Covariance matrix; Eigenvalues and eigenfunctions; Image reconstruction; Kernel; Principal component analysis; Kernel Methods; Online learning; PCA;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition (ICPR), 2010 20th International Conference on

Conference_Location

Istanbul

ISSN

1051-4651

Print_ISBN

978-1-4244-7542-1

Type

conf

DOI

10.1109/ICPR.2010.50

Filename

5597625