Re: [UAI] conditional probability question

From: Marek J. Druzdzel (marek@andrew.cmu.edu)
Date: Wed Mar 15 2000 - 15:23:07 PST

  • Next message: H.Mallinson: "[UAI] Mailing Lists for other AI topics"

    --On Wednesday, March 15, 2000, 7:53 AM -0800 Neal Rothleder and Eric
    Bloedorn <bloedorn@mitre.org> wrote:

    > We are working on a problem in for which we would like to use Bayes
    > rule, but that appears computationally infeasible. Can anyone
    > in this list suggest methods for calcuating a large number of
    > conditional probabilities required for Bayes without the independence
    > assumption?

    Bayesian networks do not force you to make any independence assumptions and
    the algorithms developed for them are pretty efficient. If you tell me
    more details/give an example, I should be able to encode it in GeNIe for
    you.
    Cheers,

    Marek
    --------------------------------------------------------------------------
    Marek J. Druzdzel http://www.pitt.edu/~druzdzel



    This archive was generated by hypermail 2b29 : Wed Mar 15 2000 - 15:25:03 PST