A factorisation of the joint probability distribution can be represented in a graph known as a Bayesian Network. These networks codify independencies between variables and information flow as variables are measured.
❦
1 Graphs
A brief introduction to graphs and DAGs and some of the associated definitions.
2 Bayesian Networks
A Bayesian Network encodes a factorisation of the joint probability distribution of a model's parameters. It's an efficient representation of the probabilistic information contained in the model.
3 Reasoning patterns in Bayesian Networks
There are several common reasoning patterns in a Bayesian Network, and this is a quick introduction without any formality.