A new Bayesian design method for support vector classification
Wei Chu, S. Sathiya Keerthi, Chong Jin Ong · 2004
We apply popular Bayesian techniques on a support vector classifier. We propose a novel differentiable loss function called trigonometric loss function with the desirable characteristic of natural normalization in the likelihood function, and then follow standard Gaussian processes techniques to set up a Bayesian framework. In this framework, Bayesian inference is used to implement model adaptation, while keeping the merits of support vector classifier, such as sparseness and convex programming. Moreover, we put forward class probability in making predictions. Experimental results on benchmark data sets indicate the usefulness of this approach.