drHugin, which is an extension of Hugin, deals with value of information in Bayesian networks. The approach taken is the myopic one, and it is based on value functions over a hypothesis variable. In this framework both utility based and utility free assessments of information sources are available. 1 Introduction Whenever decisions under uncertainty are to be made, there is a quest for more information to reduce the uncertainty. However, information is rather seldom cost free, and therefore there is also a need for evaluating on beforehand whether it is worthwhile to consult an information source. Furthermore, if several sources are available there is a need to come up with a strategy for a sequence of data requests. The problem of data request has been formally treated in decision theory (Howard 1966, Lindley 1971, Schachter 1986) where utilities of possible actions are guiding the request decisions. Also utility-free assessments of information sources have been studied (BenBassat 19...

We present two recent applications of Bayesian networks: adaptive testing and troubleshooting man-made devices. We review briefly the underlying theory and provide a general framework for building strategies using Bayesian network models. We discuss applications of the framework to adaptive testing and troubleshooting. The paper is based on our experience with two projects: a student semester project during which an adaptive test of students' knowledge of operations with fractions was designed and the SACSO project - a joint project of HewlettPackard and Aalborg University focused on development of methods for troubleshooting complex electro-mechanical systems.

mitelne reprezentaci nezavislost mezi velicinami pomoc acyklickych orientovanych grafu . Bayesovska st' je tvorena acyklickych orientovanym grafem G = (V, E), ke kaz- demu uzlu i V je prirazena jedna nahodna velicina X i s konecnou mnozinou X i navza- jem disjunktnch stavu a tabulka podmnene pravdepodobnosti P (X i (X j ) j#pa(i) ), kde pa(i) oznacuje mnozinu rodicu uzlu i v grafu G. Viz obrazek 1, kde je uveden prklad bayesovske ste. Tato prace je ceskou verz clanku publikovaneho na konferenci Znalosti 2003. Autor byl podporen grantem Grantove agentury C eske republiky cslo 201/02/1269. X4 X9 X 6 X8 X3 X5 X1 P (X1 ) P (X2 ) P (X 6 X 3 , X 4 ) X7 , X6 ) Obrazek 1. Prklad bayesovske ste Bayesovska st'reprezentuje kvalitativn i kvantitativn znalosti. Kvantitativn znalosti jsou reprezentovany pomoc tabulek podmnene pravdepodobnosti, zatmco kvalitativn znalosti pomoc acyklickeho orientovaneho grafu. Tento graf vyjadruje vztahy podm- nene nezavislosti mez

Keywords: Decision Trees are considered to be one of the most popular approaches for representing classifiers. Researchers from various disciplines such as statistics, machine learning, pattern recognition, and Data Mining have dealt with the issue of growing a decision tree from available data. This paper presents an updated survey of current methods for constructing decision tree classifiers in a top-down manner. The chapter suggests a unified algorithmic framework for presenting these algorithms and describes various splitting criteria and pruning methodologies.