Journal article
Model selection for Gaussian kernel PCA denoising
We propose kernel Parallel Analysis (kPA) for automatic kernel scale and model order selection in Gaussian kernel PCA. Parallel Analysis [1] 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 kernel PCA.We evaluate kPA for denoising of simulated data and the US 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 (SNR) of the denoised data.
Language: | English |
---|---|
Publisher: | IEEE |
Year: | 2012 |
Pages: | 163-168 |
ISSN: | 21622388 , 2162237x , 19410093 and 10459227 |
Types: | Journal article |
DOI: | 10.1109/TNNLS.2011.2178325 |
ORCIDs: | Hansen, Lars Kai |
Eigenvalues and eigenfunctions Gaussian kernel PCA denoising Gaussian processes Kernel Noise reduction Principal component analysis Signal to noise ratio Training covariance analysis handwritten character recognition handwritten digit denoising image denoising kernel parallel analysis kernel principal component analysis model order selection model selection parallel analysis principal component analysis radial basis function based KPCA radial basis function networks signal-to-noise ratio