This course provides an introduction to current research in uncertainty management, which is one of the central research areas within artificial intelligence. The principal focus of the course is on Bayesian networks, which are at the cutting edge of this research. Bayesian networks are graphical models which, unlike traditional rule-based methods, provide techniques for reasoning under conditions of uncertainty in a consistent, efficient, and mathematically sound way. While Bayesian networks are the main topic, the course examines a number of alternative formalisms as well. Specific topics include foundations of probability theory, Bayesian networks (knowledge representation and inference algorithms), belief functions (Dempster-Shafer theory), graphical models for belief functions, and fuzzy logic. Pertinent background in probability and theoretical computer science is developed as needed in the course.

Course instructor: 
Watkins