Signal Theory for SVM Kernel Parameter Estimation
James Nelson, Bob Damper, Steve Gunn and Baofeng Guo
In: 2006 IEEE International Workshop on Machine Learning For Signal Processing, 6-8 Sept 2006, Maynooth, Ireland.

This is the latest version of this eprint.

Abstract

Fourier-based regularisation is considered for the support vector machine classification problem over absolutely integrable loss functions. By invoking the modest assumption that the decision function belongs to a Paley-Wiener space, it is shown that the classification problem can be developed in the context of signal theory. Furthermore, by employing the Paley-Wiener reproducing kernel, namely the sinc function, it is shown that a principled and finite kernel hyper-parameter search space can be discerned, a priori. Subsequent experiments, performed on a commonly available hyper-spectral image data set, reveal that the approach yields results that surpass state-of-the-art benchmarks.

Available Versions of this Item

• Sparse Feature Extraction using Generalised Partial Least Squares (deposited 22 November 2006)
  • Signal Theory for SVM Kernel Parameter Estimation (deposited 23 November 2006) [Currently Displayed]

[Edit]