Despite its simplicity, the naive Bayes classifier has surprised machine learning researchers by exhibiting good performance on a variety of learning problems. Encouraged by these results, researchers have looked to overcome naive Bayes’ primary weakness—attribute independence—and improve the performance of the algorithm. This paper presents a locally weighted version of naive Bayes that relaxe...

Bayes linear kinematics and graphical models provide an extension of methods so that full conditional updates may be combined with belief adjustment. The use eliminates the problem non-commutativity which was observed in earlier work involving moment-based updates. In this paper we describe approach investigate its application to rapid computation prognostic index values survival when a patient...

‎Consider an estimation problem in a one-parameter non-regular distribution when both endpoints of the support depend on a single parameter‎. ‎In this paper‎, ‎we give sufficient conditions for a generalized Bayes estimator of a parametric function to be admissible‎. ‎Some examples are given‎. ‎

This technical note addresses some key reproducibility issues in the dynamic causal modelling of group studies of event related potentials. Specifically, we address the reproducibility of Bayesian model comparison (and inferences about model parameters) from three important perspectives namely: (i) reproducibility with independent data (obtained by averaging over odd and even trials); (ii) repr...