Non-linear modeling of a production process by hybrid Bayesian networks
Rainer Deventer, Joachim Denzler, Heinrich Niemann · 2000
Abstract. This paper shows how non-linear functions can be ap-proximated by hybrid Bayesian networks. The basic idea is to make a piecewise linear approximation with several base points. This ap-proach is applied to an engineering domain and the accuracy is com-pared to Gibbs sampling. Great accuracy is shown even at non-continuous functions. Due to the general underlying principle, it is possible to adapt this type of network to other domains. 1