Bayesian Belief Network Simulation

A Bayesain belief network is a graphical representation of the underlying probabilistic relationships of a complex system. These networks are used for reasoning with uncertainty, such as in decision support systems. This requires probabilistic inference with Bayesian belief networks. Simulation schemes for probabilistic inference with Bayesian belief networks offer many advantages over exact inference algorithms. The use of randomly generated Bayesian belief networks is a good way to test the robustness and convergence of simulation schemes. In this report, we first present methods for random generations of Bayesian belief networks, then we implement stochastic simulation algorithms for probabilistic inference with such networks. Since random number generators play a critical role in random generations of belief networks, we explore the theoretical and practical backgrounds of random number generators and select suitable generators for our project.