: This article describes a propagation scheme for Bayesian networks with conditional Gaussian distributions that does not have the numerical weaknesses of the scheme derived in Lauritzen (1992). The propagation architecture is that of Lauritzen and Spiegelhalter (1988). In addition to the means and variances provided by the previous algorithm, the new propagation scheme yields full local marginal distributions. The new scheme also handles linear deterministic relationships between continuous variables in the network specification. The new propagation scheme is in many ways faster and simpler than previous schemes and the method has been implemented in the most recent version of the HUGIN software. Key words: Artificial intelligence, Bayesian networks, CG distributions, Gaussian mixtures, probabilistic expert systems, propagation of evidence. 1 Introduction Bayesian networks have developed into an important tool for building systems for decision support in environments characterized by...

Chain graphs are a natural generalization of directed acyclic graphs (DAGs) and undirected graphs. However, the apparent simplicity of chain graphs belies the subtlety of the conditional independence hypotheses that they represent. There are a number of simple and apparently plausible, but ultimately fallacious interpretations of chain graphs that are often invoked, implicitly or explicitly. These interpretations also lead to awed methods for applying background knowledge to model selection. We present a valid interpretation by showing how the distribution corresponding to a chain graph may be generated as the equilibrium distribution of dynamic models with feedback. These dynamic interpretations lead to a simple theory of intervention, extending the theory developed for DAGs. Finally, we contrast chain graph models under this interpretation with simultaneous equation models which have traditionally been used to model feedback in econometrics. Keywords: Causal model; cha...

We present a technique that, given a sequence of musical note onset times, performs simultaneous identification of the norated rhythm and the variable tempo associated with the times. Our formulation is probabilistic: We develop a stochastic model for the interconnected evolution of a rhythm process, a tempo process, and an observable process. This model allows the globally optimal identification of the most likely rhythm and tempo sequence, given the observed onset times. We demonstrate applications to a sequence of times derived from a sampled audio file and to MIDI data.

A method is presented for the rhythmic parsing problem: Given a sequence of observed musical note onset times, we simultaneously estimate the corresponding norated rhythm and tempo process. A graphical model is developed that represents the evolution of tempo and rhythm and relates these hidden quantities to an observable performance. The rhythm variables are discrete and the tempo and observation variables are continuous. We show how to compute the globally most likely configuration of the tempo and rhythm variables given an observation of note onset times. Experiments are presented on both MIDI data and a data set derived from an audio signal. A generalization to computing MAP estimates for arbitrary conditional Gaussian distributions is outlined.

Recursive graphical models usually underlie the statistical modelling concerning probabilistic expert systems based on Bayesian networks. This paper defines a version of these models, denoted as recursive exponential models, which have evolved by the desire to impose sophisticated domain knowledge onto local fragments of a model. Besides the structural knowledge, as specified by a given model, the statistical modelling may also include expert opinion about the values of parameters in the model. It is shown how to translate imprecise expert knowledge into approximately conjugate prior distributions. Based on possibly incomplete data, the score and the observed information are derived for these models. This accounts for both the traditional score and observed information, derived as derivatives of the log-likelihood, and the posterior score and observed information, derived as derivatives of the log-posterior distribution. Throughout the paper the specialization int...

Most of the Bayesian network-based classifiers are usually only able to handle discrete variables. However, most real-world domains involve continuous variables. A common practice to deal with continuous variables is to discretize them, with a subsequent loss of information. This work shows how discrete classifier induction algorithms can be adapted to the conditional Gaussian network paradigm to deal with continuous variables without discretizing them. In addition, three novel classifier induction algorithms and two new propositions about mutual information are introduced. The classifier induction algorithms presented are ordered and grouped according to their structural complexity: naive Bayes, tree augmented naive Bayes, k-dependence Bayesian classifiers and semi naive Bayes. All the classifier induction algorithms are empirically evaluated using predictive accuracy, and they are compared to linear discriminant analysis, as a continuous classic statistical benchmark classifier. Besides, the accuracies for a set of state-of-the-art classifiers are included in order to justify the use of linear discriminant analysis as the benchmark algorithm. In order to understand the behavior of the conditional Gaussian network-based classifiers better, the results include bias-variance decomposition of the expected misclassification rate. The study suggests that semi naive Bayes structure based classifiers and, especially, the novel wrapper condensed semi naive Bayes backward, outperform the behavior of the rest of the presented classifiers. They also obtain quite competitive results compared to the state-of-the-art algorithms included. Key words: conditional Gaussian network, Bayesian network, naive Bayes, tree augmented naive Bayes, k-dependence Bayesian classifiers, semi naive Bayes, filter, wrapper.

This paper deals with chain graph models under alternative AMP interpretation. A new representative of an AMP Markov equivalence class, called the largest deflagged graph, is proposed. The representative is based on revealed internal structure of the AMP Markov equivalence class. More specifically, the AMP Markov equivalence class decomposes into finer strong equivalence classes and there exists a distinguished strong equivalence class among those forming the AMP Markov equivalence class. The largest deflagged graph is the largest chain graph in that distinguished strong equivalence class. A composed graphical procedure to get the largest deflagged graph on the basis of any AMP Markov equivalent chain graph is presented. In general, the largest deflagged graph differs from the AMP essential graph, which is another representative of the AMP Markov equivalence class.

The theoretical background for a program for establishing expert systems on the basis of observations and expert knowledge is presented. Block recursive models form the basis of the statistical modelling. These models, together with various model selection methods for automatic model selection, are presented. Additionally, the connection between a block recursive model and expert systems based on causal probabilistic networks is treated. A medical example concerning diagnosis of coronary artery disease forms the basis for an evaluation of the expert systems established. Keywords: causal probabilistic networks, graphical association models, machine learning, model selection, selection criteria, selection strategies. 1 Introduction BIFROST is a program for semi-automatic knowledge acquisition and is a continuation developments made in (Greve, Hjsgaard, Skjth and Thiesson 1990). The objective is to obtain preliminary causal models for use in the HUGIN expert system shell (Ander...

We present methodology for identifying the most likely configuration of unobserved variables, given observed variables, for collections of discrete and continuous variables with conditional Gaussian (CG) distributions. The dependency structure on the joint distribution of discrete and continuous variables is represented in terms of a directed acyclic graph (DAG) in which continuous variables do not have discrete children. The joint distribution is then factored as a product of potentials, each depending only on the variables in a clique of a triangulation of the moralized DAG. A dynamic programming method is developed in which a clique potential is represented as a maximum of a finite number of Gaussian kernels.

The shared mixture classifier extends the conditional mixture classifier by allowing all the mixture components to contribute to the feature density model. We consider mixtures of elliptically symmetrical densities, and provide gradient ascent and expectation maximisation algorithms for maximum likelihood estimation. Three criteria are examined: the joint, non-discriminative and discriminative likelihoods. The relationships between these criteria are discussed, and we compare the performance of shared and conditional mixture classifiers. Results are presented for an application of a shared mixture classifier to the problem of detecting buried land mines using infrared and visual imagery. They show consistently better performance from the shared model.