A leave-k-out cross-validation scheme for unsupervised kernel regression

Authors:
Stefan Klanke;Helge Ritter
Affiliations:
Neuroinformatics Group, Faculty of Technology, University of Bielefeld, Bielefeld, Germany;Neuroinformatics Group, Faculty of Technology, University of Bielefeld, Bielefeld, Germany
Venue:
ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
Year:
2006

Citing 4
Cited 3

GTM: the generative topographic mapping

Neural Computation
Regularized Principal Manifolds

EuroCOLT '99 Proceedings of the 4th European Conference on Computational Learning Theory
Laplacian Eigenmaps for dimensionality reduction and data representation

Neural Computation
Principal Surfaces from Unsupervised Kernel Regression

IEEE Transactions on Pattern Analysis and Machine Intelligence

Variants of unsupervised kernel regression: General cost functions

Neurocomputing
Salient feature and reliable classifier selection for facial expression classification

Pattern Recognition
Integrating feature maps and competitive layer architectures for motion segmentation

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We show how to employ leave-K-out cross-validation in Unsupervised Kernel Regression, a recent method for learning of nonlinear manifolds. We thereby generalize an already present regularization method, yielding more flexibility without additional computational cost. We demonstrate our method on both toy and real data.