Uncertainty in an Unknown World
Recent advances in knowledge representation for probability models have allowed for uncertainty about the properties of objects and the relations that might hold among them. Such models, however, typically assume exact knowledge of which objects exist and of which object is which---that is, they assume *domain closure* and *unique names*.
These assumptions simplify the sample space for probability models, but are inappropriate for many real-world situations. This talk presents a formal language, BLOG, for defining probability models over worlds with unknown objects in which several terms may refer to the same object. BLOG models define generative processes that combine "factual" events that specify relationships among objects with "existence" events that generate the objects themselves. Subject to certain acyclicity constraints, every BLOG model specifies a unique probability distribution over the set of possible worlds for the first-order language. Furthermore, complete inference algorithms exist for a useful fragment of the language. I will present several example models and discuss interesting issues arising from the treatment of evidence in such languages.
[Joint work with Brian Milch, Bhaskara Marthi, Hanna Pasula, David Sontag, Andrey Kolobov, and Daniel Ong]
Stuart Russell received his B.A. with first-class honors in physics from Oxford University in 1982 and his Ph.D. in computer science from Stanford in 1986. He then joined the faculty of the University of California, Berkeley, where he is professor and chairman of computer science, director of the Center for Intelligent Systems, and holder of the Smith--Zadeh Chair in Engineering. In 1990, he received the Presidential Young Investigator Award of the National Science Foundation; in 1995 he was co-winner of the Computers and Thought Award; and in 2005 he won the ACM Karlstrom Outstanding Educator Award. He was a 1996 Miller Professor of the University of California and was appointed to a Chancellor's Professorship in 2000. In 1998, he gave the Forsythe Memorial Lectures at Stanford University. He is a Fellow and former Executive Council member of the American Association for Artificial Intelligence, a Fellow of the Association for Computing Machinery, and Secretary of the International Machine Learning Society. He has published around 150 papers on a wide range of topics in artificial intelligence. His books include "The Use of Knowledge in Analogy and Induction" (Pitman, 1989) and "Do the Right Thing: Studies in Limited Rationality" (with Eric Wefald, MIT Press, 1991), as well as the standard textbook in the field, "Artificial Intelligence: A Modern Approach" (with Peter Norvig, Prentice Hall, 1995, 2003).
INSTITUTE for GENOMICS and BIOINFORMATICS
2006-2007 Distinguished Speaker Series in Artificial Intelligence/Machine Learning.
Reservations requested to Michele McCrea at firstname.lastname@example.org
No cost to attend - Seating is limited and on a first-come, first-served basis
*Registration is Required