"Directed graphical models are a type of probabilistic models where all the variables are topologically organized into a directed acyclic graph." Kingma. (2019). An Introduction to Variational Autoencoders. Foundations and Trends in Machine Learning.
"We work with directed probabilistic models, also called directed probabilistic graphical models (PGMs), or Bayesian networks." Kingma. (2019). An Introduction to Variational Autoencoders. Foundations and Trends in Machine Learning.
"The joint distribution over the variables of such models factorizes as a product of prior and conditional distributions" Kingma. (2019). An Introduction to Variational Autoencoders. Foundations and Trends in Machine Learning.
