So far, the models have been divided into two categories: static and dynamic. In static modelling, each observation or data sample is independent of the others. In dynamic models, the relations between consecutive observations are modelled. The generalisation of both is that the relations are described in the data itself, that is, each observation might have a different model structure. The following two chapters concentrate on relational models. One of the models, nonlinear relational Markov network (see Section 6.3), is implemented using Bayes Blocks.