Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings         Authors   Author's Info   Article details         Search    
The Bounded Bayesian
Kathryn Laskey
Abstract:
The ideal Bayesian agent reasons from a global probability model, but real agents are restricted to simplified models which they know to be adequate only in restricted circumstances. Very little formal theory has been developed to help fallibly rational agents manage the process of constructing and revising small world models. The goal of this paper is to present a theoretical framework for analyzing model management approaches. For a probability forecasting problem, a search process over small world models is analyzed as an approximation to a larger-world model which the agent cannot explicitly enumerate or compute. Conditions are given under which the sequence of small-world models converges to the larger-world probabilities.
Keywords:
Pages: 159-165
PS Link:
PDF Link: /papers/92/p159-laskey.pdf
BibTex:
@INPROCEEDINGS{Laskey92,
AUTHOR = "Kathryn Laskey ",
TITLE = "The Bounded Bayesian",
BOOKTITLE = "Proceedings of the Eighth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-92)",
PUBLISHER = "Morgan Kaufmann",
ADDRESS = "San Mateo, CA",
YEAR = "1992",
PAGES = "159--165"
}


hosted by DSL   •   site info   •   help