<< Click to Display Table of Contents >> Navigation:  Using SMILE > Dynamic Bayesian networks

A Bayesian network is a snapshot of the world at a given time and is used to model systems that are in some kind of equilibrium state. Unfortunately, most systems in the world change over time and sometimes we would like to know how these systems evolve over time.

A dynamic Bayesian network (DBN) is a Bayesian network extended with additional mechanisms that are capable of modeling influences over time. The temporal extension of BNs does not mean that the network structure or parameters changes dynamically, but that a dynamic system is modeled. In other words, the underlying process, modeled by a DBN, is stationary. A DBN is a model of a stochastic process.

The implementation of DBNs in SMILE allows for use both chance (CPT and canonical) and deterministic node types in dynamic models.

Tutorial 6 contains a complete program demonstrating the use of DBNs.