Robust Cross-Validation Score Function for Non-linear Function Estimation

Authors:
Jos De Brabanter;Kristiaan Pelckmans;Johan A. K. Suykens;Joos Vandewalle
Affiliations:
-;-;-;-
Venue:
ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Year:
2002

Citing 2
Cited 4

The nature of statistical learning theory

The nature of statistical learning theory
Least Squares Support Vector Machine Classifiers

Neural Processing Letters

Additive Regularization Trade-Off: Fusion of Training and Validation Levels in Kernel Methods

Machine Learning
The differogram: Non-parametric noise variance estimation and its use for model selection

Neurocomputing
LSSVM parameters optimizing and non-linear system prediction based on cross validation

ICNC'09 Proceedings of the 5th international conference on Natural computation
Asymmetric least squares support vector machine classifiers

Computational Statistics & Data Analysis

Quantified Score

Hi-index	0.03

Visualization

Abstract

In this paper a new method for tuning regularisation parameters or other hyperparameters of a learning process (non-linear function estimation) is proposed, called robust cross-validation score function (CVS-fold)Robust). CVS-fold)Robust is effective for dealing with outliers and non-Gaussian noise distributions on the data. Illustrative simulation results are given to demonstrate that the CVS-fold)Robust method outperforms other cross-validation methods.