The articles below describe projects that do this. Max "The sensitivity of belief networks to imprecise probabilities: An experimental investigation", Pradhan, M., Henrion, M., Provan, G., Del Favero, B., and Huang, K., Artificial Intelligence Journal, Vol: 84, Issue: 1-2, Jul 1996, pp. 357. "Probabilistic diagnosis using a reformulation of the Internist-1/QMR Knowledge Base: I. The probabilistic model and inference algorithms", Shwe M, Middleton B, Heckerman DE, Henrion M, Horvitz EJ, Lehman H and Cooper GF, Methods of Information in Medicine, 30, 1991, 241-55. "Probabilistic diagnosis using a reformulation of the Internist-1/QMR Knowledge Base: II. Evaluation of diagnostic performance", Middleton B, Shwe M, Heckerman DE, Henrion M, Horvitz EJ, Lehman H and Cooper GF, Methods of Information in Medicine, 30, 1991, 256-67. "An Experimental Comparison of Knowledge Engineering for Decision Analysis and for Expert Systems", Max Henrion & Daniel Cooley, Proceedings of AAAI-87, American Association for Artificial Intelligence, July, 1987, pp471-477. > -----Original Message----- > From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]]On Behalf Of > [EMAIL PROTECTED] > Sent: Monday, August 02, 1999 12:37 PM > To: [EMAIL PROTECTED] > Subject: looking for article on transforming production-rule-based > systems to bayes nets > > > I'm trying to find articles that compare traditional > rule-based systems to > bayes nets. I remember having read an article once about a > project that > sought to reengineer an existing knowledge based system to a Bayesian > approach, but can't remember where or from whom. > > Any pointers? > > greetings, > Hans van Leijen. > > ======================================================= > Hans van Leijen ([EMAIL PROTECTED]) > ======================================================= > Everest bv > Reitscheweg 55 > 5232 BX 's-Hertogenbosch > The Netherlands > > T +31 (0)73 645 04 60 > F +31 (0)73 645 09 20 > ======================================================= > A PinkRoccade nv Company > ======================================================= > > >
