In this paper we want to achieve an approximation algorithm for Bayesian networks using data. At first we want to make a description of Bayesian networks and then talk about their modeling of the data using approximation algorithm PNM.

Given the values of a measurable function m:Rd→R at n arbitrarily chosen points in Rd the problem of estimating m on whole Rd is considered. Here the estimate has to be defined such that the L1 error of the estimate (with integration with respect to a fixed but unknown probability measure) is...