In this paper we present a simple hierarchical Bayesian treatment of the sparse kernel logistic regression (KLR) model based MacKay’s evidence approximation. The model is re-parameterised such that an isotropic Gaussian prior over parameters in the kernel induced feature space is replaced by an isotropic Gaussian prior over the transformed parameters, facilitating a Bayesian analysis using standard methods. The Bayesian approach allows the selection of “good” values for the usual regularisation and kernel parameters through maximisation of the marginal likelihood. Results obtained on a variety of benchmark datasets are provided indicating that the Bayesian kernel logistic regression model is competitive, whilst having one less parameter to determine during model selection.
|Number of pages||6|
|Publication status||Published - Apr 2004|
|Event||European Symposium on Artificial Neural Networks - Bruges, Belgium|
Duration: 28 Apr 2004 → 30 Apr 2004
|Conference||European Symposium on Artificial Neural Networks|
|Period||28/04/04 → 30/04/04|