One of the fundamental issues of Bayesian networks is their representational power, re-ecting what kind of functions they can or cannot represent. In this paper, we rst prove an upper bound on the representational power of Augmented Naive Bayes. We then extend the result to general Bayesian networks. Roughly speaking, if a function contains an m-XOR, there exists no Bayesian networks with node ...

We present a system detecting the presence of unconstrained man-made objects in unconstrained subsea videos. Classification is based on contours, which are reasonably stable features in underwater imagery. First, the system determines automatically an optimal scale for contour extraction by optimising a quality metric. Second, a two-feature Bayesian classifier determines whether the image conta...

The design of an optimal Bayesian classifier for multiple features is dependent on the estimation of multidimensional joint probability density functions and therefore requires a design sample size that increases exponentially with the number of dimensions. A method was developed that combines classification decisions from marginal density functions using an additional classifier. Unlike voting...

A useful method for representing Bayesian classifiers is through discriminant functions. Here, using copula functions, we propose a new model for discriminants. This model provides a rich and generalized class of decision boundaries. These decision boundaries significantly boost the classification accuracy especially for high dimensional feature spaces. We strengthen our analysis through simula...

Classifying human cognitive states using fMRI data is an interesting and challenging problem that would guide us to better understanding about human brain. In this paper we introduce TAN classifier to distinguish whether subjects are examining a sentence or a picture. Experiments show that using this TAN classifiers provides significantly better results than using Naive Bayes classifiers.

Probabilistic record linkage has been well investigated in recent years. The Fellegi-Sunter probabilistic record linkage and its enhanced version are commonly used methods, which calculate match and non-match weights for each pair of corresponding fields of record-pairs. Bayesian network classifiers – naive Bayes classifier and TAN have also been successfully used here. Very recently, an extend...

This paper makes use of Hierarchical Bayes Models to model and estimate spatial health effects. We focus on Germany, combining rich individual-level household panel data with administrative county– level information to estimate spatial county-level health dependencies. As dependent variable, we use the generic, continuous, and quasi-objective SF12 health measure. Our findings reveal strong and ...

The publisher does not give any warranty express or implied or make any representation that the contents will be complete or accurate or up to date. The accuracy of any instructions, formulae and drug doses should be independently verified with primary sources. The publisher shall not be liable for any loss, actions, claims, proceedings, demand or costs or damages whatsoever or howsoever caused...

A max-2-connected Bayes network is one where there are at most 2 distinct directed paths between any two nodes. We show that even for this restricted topology, null-evidence belief updating is hard to approximate.