This paper provides a tutorial on Bayesian networks and associated Bayesian techniques for extracting and encoding knowledge from data. Bayesian networks are graphical models that encode probabilistic relationships among variables. They are particularly useful for handling incomplete data, learning causal relationships, and combining prior knowledge with data. The paper discusses methods for constructing Bayesian networks from prior knowledge and summarizes Bayesian statistical methods for using data to improve these models. It describes techniques for learning both the parameters and structure of a Bayesian network, including methods for learning with incomplete data. The paper also relates Bayesian-network methods for learning to techniques for supervised and unsupervised learning. A real-world case study is used to illustrate the graphical-modeling approach. The paper also discusses the Bayesian approach to probability and statistics, emphasizing that Bayesian probability is a person's degree of belief in an event, rather than a physical property of the world. The paper explains how Bayesian networks can be used to model and learn from data, including methods for probabilistic inference and learning probabilities in a Bayesian network. It also discusses methods for handling incomplete data, including Monte-Carlo methods and the Gaussian approximation. The paper concludes with a discussion of the importance of Bayesian methods in avoiding overfitting of data and the role of Bayesian networks in combining prior knowledge with data.This paper provides a tutorial on Bayesian networks and associated Bayesian techniques for extracting and encoding knowledge from data. Bayesian networks are graphical models that encode probabilistic relationships among variables. They are particularly useful for handling incomplete data, learning causal relationships, and combining prior knowledge with data. The paper discusses methods for constructing Bayesian networks from prior knowledge and summarizes Bayesian statistical methods for using data to improve these models. It describes techniques for learning both the parameters and structure of a Bayesian network, including methods for learning with incomplete data. The paper also relates Bayesian-network methods for learning to techniques for supervised and unsupervised learning. A real-world case study is used to illustrate the graphical-modeling approach. The paper also discusses the Bayesian approach to probability and statistics, emphasizing that Bayesian probability is a person's degree of belief in an event, rather than a physical property of the world. The paper explains how Bayesian networks can be used to model and learn from data, including methods for probabilistic inference and learning probabilities in a Bayesian network. It also discusses methods for handling incomplete data, including Monte-Carlo methods and the Gaussian approximation. The paper concludes with a discussion of the importance of Bayesian methods in avoiding overfitting of data and the role of Bayesian networks in combining prior knowledge with data.