Reference Subject: Re: Re; [UAI} Definition of a Bayesian Network From: Kathryn Blackmond Laskey <[EMAIL PROTECTED]> Date: Wed, 29 Aug 2001 12:18:20 -0700 Sender: [EMAIL PROTECTED] In her mail, Kathy expresses her feeling that probability theory had an excellent semantic, whereas fuzzy set theory misses it. I like to point that a full semantic about possibility theory is described in the next two papers, and that this semantic provides a semantic for fuzzy set theory. The first paper presents a semantic for subjective possibility functions and is based on the same kind of semantic as used for Bayesian probabilities, i.e., betting behavior. The second paper presents the same semantic plus another semantic for objective possibility functions. Interested readers can downloaded these 2 papers from my web site, address below. Comments are welcome. Philippe Smets Smets Ph.(2000) Quantitative Epistemic Possibility Theory seens as an Hyper Cautious Transferable Belif Model. LFA La Rochelle, TR/IRIDIA-2000-18 Providing a semantic to the values given to the degrees of possibility. Based on the TBM and cautious combination rules. Possib_Semantic.ps Possib_Semantic.pdf Dubois D., Prade H. and Smets Ph. (2001) New Semantics for Quantitative Possibility Theory. ISIPTA'01. Ithaca, NY. Semantic for both the subjective and objective possibility measures. SemanticPossSubjObj.pdf - -- ******************************************** Philippe Smets email: [EMAIL PROTECTED] web: http://iridia.ulb.ac.be/~psmets Institut de Recherches Interdisciplinaires et de Developements en Intelligence Artificielle. IRIDIA-CP 194/6, Universite Libre de Bruxelles 50 av. Roosevelt, 1050 Bruxelles, Belgium. tel 32 2 650 27 29 secretary, 32 2 344 82 96 private (where I am usually) fax: 32 2 650 27 15 GSM: 32 495 50 10 72
