This section introduces the fundamental concepts, terminology, and notation of Bayesian networks. A Bayesian network models a set of variables and their joint probability distribution using a directed acyclic graph (DAG). Each variable can take on discrete or continuous states, and the network encodes conditional independence relationships among the variables. The joint probability distribution is decomposed into local conditional probability distributions, which are specified for each variable conditioned on its parents in the DAG. The structure of the network directly reflects these conditional independencies. The section also discusses the practical construction of Bayesian networks using cause-and-effect relationships, and introduces models like the noisy-OR model to simplify the specification of complex interactions. It explains how Bayesian networks can be used for probabilistic inference, including exact and approximate methods, and highlights the computational challenges of exact inference in arbitrary Bayesian networks. Despite these challenges, Bayesian networks remain valuable for many applications due to their ability to handle complex dependencies and provide principled ways to update beliefs based on new evidence.This section introduces the fundamental concepts, terminology, and notation of Bayesian networks. A Bayesian network models a set of variables and their joint probability distribution using a directed acyclic graph (DAG). Each variable can take on discrete or continuous states, and the network encodes conditional independence relationships among the variables. The joint probability distribution is decomposed into local conditional probability distributions, which are specified for each variable conditioned on its parents in the DAG. The structure of the network directly reflects these conditional independencies. The section also discusses the practical construction of Bayesian networks using cause-and-effect relationships, and introduces models like the noisy-OR model to simplify the specification of complex interactions. It explains how Bayesian networks can be used for probabilistic inference, including exact and approximate methods, and highlights the computational challenges of exact inference in arbitrary Bayesian networks. Despite these challenges, Bayesian networks remain valuable for many applications due to their ability to handle complex dependencies and provide principled ways to update beliefs based on new evidence.