Bayesian Models of Brain and Behaviour

Figure 4

An example of a Directed Acyclic Graph (DAG). This tells us we can write the joint density over all variables as 𝑝(𝑥)=𝑝(𝑥₁)𝑝(𝑥₂)𝑝(𝑥₃∣𝑥₁)𝑝(𝑥₄∣𝑥₁,𝑥₂)𝑝(𝑥₅∣𝑥₄). DAGs provide a graphical shorthand for specifying Bayesian generative models.