Model Selection for Gaussian Kernel PCA Denoising
Authors:
- 15 December 2011
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 23 (1) , 163-168
Abstract
We propose kernel parallel analysis (kPA) for automatic kernel scale and model order selection in Gaussian kernel principal component analysis (KPCA). Parallel analysis is based on a permutation test for covariance and has previously been applied for model order selection in linear PCA, we here augment the procedure to also tune the Gaussian kernel scale of radial basis function based KPCA. We evaluate kPA for denoising of simulated data and the U.S. postal data set of handwritten digits. We find that kPA outperforms other heuristics to choose the model order and kernel scale in terms of signal-to-noise ratio of the denoised data.Keywords
This publication has 11 references indexed in Scilit:
- KPCA denoising and the pre-image problem revisitedDigital Signal Processing, 2008
- Normalization and preimage problem in gaussian kernel PCA2008
- Connecting the Out-of-Sample and Pre-Image Problems in Kernel Methods2007
- The Pre-Image Problem in Kernel MethodsIEEE Transactions on Neural Networks, 2004
- Generalizable Patterns in Neuroimaging: How Many Principal Components?NeuroImage, 1999
- Nonlinear Component Analysis as a Kernel Eigenvalue ProblemNeural Computation, 1998
- Iterative methods for the computation of a few eigenvalues of a large symmetric matrixBIT Numerical Mathematics, 1996
- A database for handwritten text recognition researchIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994
- The Guttman-Kaiser Criterion as a Predictor of the Number of Common FactorsJournal of the Royal Statistical Society: Series D (The Statistician), 1982
- A Rationale and Test for the Number of Factors in Factor AnalysisPsychometrika, 1965