Uncertainty in Artificial Intelligence
First Name   Last Name   Password   Forgot Password   Log in!
    Proceedings         Authors   Author's Info   Article details         Search    
An Empirical Analysis of Likelihood-Weighting Simulation on a Large, Multiply-Connected Belief Network
Michael Shwe, Gregory Cooper
Abstract:
We analyzed the convergence properties of likelihood- weighting algorithms on a two-level, multiply connected, belief-network representation of the QMR knowledge base of internal medicine. Specifically, on two difficult diagnostic cases, we examined the effects of Markov blanket scoring, importance sampling, demonstrating that the Markov blanket scoring and self-importance sampling significantly improve the convergence of the simulation on our model.
Keywords:
Pages: 498-508
PS Link:
PDF Link: /papers/90/p498-shwe.pdf
BibTex:
@INPROCEEDINGS{Shwe90,
AUTHOR = "Michael Shwe and Gregory Cooper",
TITLE = "An Empirical Analysis of Likelihood-Weighting Simulation on a Large, Multiply-Connected Belief Network",
BOOKTITLE = "Proceedings of the Sixth Conference Annual Conference on Uncertainty in Artificial Intelligence (UAI-90)",
PUBLISHER = "AUAI Press",
ADDRESS = "Corvallis, Oregon",
YEAR = "1990",
PAGES = "498--508"
}


hosted by DSL   •   site info   •   help