Bayesian Networks

A Personal Journey into Bayesian Networks

May, 2018

Abstract

This report contains personal memories from the years that Bayesian networks were developed, 1978-1988. It was written as a section in The Book of Why: The new science of cause and effect (Pearl and Mackenzie, 2018) but was taken out to meet space limitations. I am archiving these memories with the hope that they will prove useful for future archivists.

Introduction to Graphical Models and Bayesian Networks

Graphical models are a marriage between probability theory and graph theory. They provide a natural tool for dealing with two problems that occur throughout applied mathematics and engineering -- uncertainty and complexity -- and in particular they are playing an increasingly important role in the design and analysis of machine learning algorithms. Fundamental to the idea of a graphical model is the notion of modularity -- a complex system is built by combining simpler parts.