We describe scoring metrics for learning Bayesian networks from a combination of user knowledge and statistical data. We identify two important properties of metrics, which we call event equivalence and parameter modularity. These properties have been mostly ignored, but when combined, greatly simplify the encoding of a user’s prior knowledge. In particular, a user can express his knowledge—for the most part—as a single prior Bayesian network for the domain. 1

This literature review discusses different methods under the general rubric of learning Bayesian networks from data, and includes some overlapping work on more general probabilistic networks. Connections are drawn between the statistical, neural network, and uncertainty communities, and between the different methodological communities, such as Bayesian, description length, and classical statistics. Basic concepts for learning and Bayesian networks are introduced and methods are then reviewed. Methods are discussed for learning parameters of a probabilistic network, for learning the structure, and for learning hidden variables. The presentation avoids formal definitions and theorems, as these are plentiful in the literature, and instead illustrates key concepts with simplified examples. Keywords--- Bayesian networks, graphical models, hidden variables, learning, learning structure, probabilistic networks, knowledge discovery. I. Introduction Probabilistic networks or probabilistic gra...

Approaches to learning Bayesian networks from data typically combine a scoring metric with a heuristic search procedure. Given aBayesian network structure, many of the scoring metrics derived in the literature return a score for the entire equivalence class to which the structure belongs. When using such a metric, it is appropriate for the heuristic search algorithm to searchover equivalence classes of Bayesian networks as opposed to individual structures. We present the general formulation of a search space for which the states of the search correspond to equivalence classes of structures. Using this space, anyoneofanumber of heuristic searchalgorithms can easily be applied. We compare greedy search performance in the proposed search space to greedy search performance in a search space for which the states correspond to individual Bayesian network structures. 1

Algorithms for learning Bayesian networks from data have two components: a scoring metric and a search procedure. The scoring metric computes a score reflecting the goodness-of-fit of the structure to the data. The search procedure tries to identify network structures with high scores. Heckerman et al. (1994) introduced a Bayesian metric, called the BDe metric, that computes the relative posterior probability of a network structure given data. They show that the metric has a property desireable for inferring causal structure from data. In this paper, we show that the problem of deciding whether there is a Bayesian network---among those where each node has at most k parents---that has a relative posterior probability greater than a given constant is NP-complete, when the BDe metric is used. 1 Introduction Recently, many researchers have begun to investigate methods for learning Bayesian networks, including Bayesian methods [Cooper and Herskovits, 1991, Buntine, 1991, York 1992, Spiegel...

Previous algorithms for the recovery of Bayesian belief network structures from data have been either highly dependent on conditional independence (CI) tests, or have required on ordering on the nodes to be supplied by the user. We present an algorithm that integrates these two approaches: CI tests are used to generate an ordering on the nodes from the database, which is then used to recover the underlying Bayesian network structure using a non-Cl-test-based method. Results of the evaluation of the algorithm on a number of databases (e.g., ALARM, LED, and SOYBEAN) are presented. We also discuss some algorithm performance issues and open problems.

In this work we introduce a methodology based on Genetic Algorithms for the automatic induction of Bayesian Networks from a file containing cases and variables related to the problem. The methodology is applied to the problem of predicting survival of people after one, three and five years of being diagnosed as having malignant skin melanoma. The accuracy of the obtained model, measured in terms of the percentage of well-classified subjects, is compared to that obtained by the called Naive-Bayes. In both cases, the estimation of the model accuracy is obtained from the 10-fold cross-validation method. 1. Introduction Expert systems, one of the most developed areas in the field of Artificial Intelligence, are computer programs designed to help or replace humans beings in tasks in which the human experience and human knowledge are scarce and unreliable. Although, there are domains in which the tasks can be specifed by logic rules, other domains are characterized by an uncertainty inherent...

In this paper we present a ne_(l n [!ii ' with respect to Bayesian networks con- ogy for inducing Bayesian network structures frop3 titute the roblem of the evidence propagation and a database of cases. The methodology is based oap&lll searching for the best ordering of the system vari- the problem of the model search. The problem of shies by means of genetic algorithl{. Since his th_vidence propagation consists of once the vMproblem of finding an optimal ordea. teeuarue}rables are known, the assignment of resembles the traveling salesman p'FolUleh)ve use .... IW. ....... probablhles to the values of the rest of the van genetic operators that were developed for the latter - problem. The quality of a variable ordering is eval- ables. Cooper [4] demonstrated that this problem Mated with the algorithm K2. We present empirical results that were obtained with a simulation of the ALARM network.

This paper was partially presented at the 9th conference on Uncertainty in Artificial Intelligence, July 1993.

We extend the Bayesian Information Criterion (BIC), an asymptotic approximation for the marginal likelihood, to Bayesian networks with hidden variables. This approximation can be used to select models given large samples of data. The standard BIC as well as our extension punishes the complexity of a model according to the dimension of its parameters. We argue that the dimension of a Bayesian network with hidden variables is the rank of the Jacobian matrix of the transformation between the parameters of the network and the parameters of the observable variables. We compute the dimensions of several networks including the naive Bayes model with a hidden root node. 1

Abstract not found