Colloquia: Bayesian Learning of Bayesian Networks
Date/Time: | Thursday, 15 Oct 2009 at 3:40 pm |
---|---|
Location: | B29 Atanasoff |
Cost: | free |
Phone: | 515-294-6516 |
Channel: | College of Liberal Arts and Sciences |
Categories: | Lectures |
Actions: | Download iCal/vCal | Email Reminder |
In recent years, Bayesian networks have become increasingly popular for representing and reasoning about uncertainty and causality. A Bayesian network provides a compact representation of a joint probability over a set of variables, and supports efficient algorithms for answering probabilistic queries. They are being used in a variety of domains such as diagnosis, data mining, pattern recognition, sensor fusion, and computational biology. One major challenge in the applications of Bayesian networks is to learn the structure of a Bayesian network model from data. In this talk I will introduce Bayesian methods for structure learning, and present an algorithm that can compute the exact posterior probabilities of structural features in Bayesian networks of a moderate size.
Jin Tian received his PhD in computer science from UCLA in 2002. He is an assistant professor in the Department of Computer Science at Iowa State University. His research interests are primarily in the areas of artificial intelligence and machine learning with current research focusing on probabilistic reasoning and causal inference in graphical models.