Piero Bonissone, Bruce D'Ambrosio, Philippe Smets
This is the Proceedings of the Seventh Conference on Uncertainty in Artificial Intelligence, which was held in Los Angeles, CA, July 13-15, 1991
Bruce D'Ambrosio, Didier Dubois, Philippe Smets et al.
This is the Proceedings of the Eighth Conference on Uncertainty in Artificial Intelligence, which was held in Stanford, CA, July 17-19, 1992
Philippe Smets
We derive axiomatically the probability function that should be used to make decisions given any form of underlying uncertainty.
Philippe Smets, Yen-Teh Hsia
Inappropriate use of Dempster's rule of combination has led some authors to reject the Dempster-Shafer model, arguing that it leads to supposedly unacceptable conclusions when defaults are involved. A most classic example is about the penguin Tweety. This paper will successively present: the origin of the miss-management of the Tweety example; two types of default; the correct solution for both types based on the transferable belief model (our interpretation of the Dempster-Shafer model (Shafer 1976, Smets 1988)); Except when explicitly stated, all belief functions used in this paper are simple support functions, i.e. belief functions for which only one proposition (the focus) of the frame of discernment receives a positive basic belief mass with the remaining mass being given to the tautology. Each belief function will be described by its focus and the weight of the focus (e.g. m(A)=.9). Computation of the basic belief masses are always performed by vacuously extending each belief function to the product space built from all variables involved, combining them on that space by Dempster's rule of combination, and projecting the result to the space corresponding to each individual variable.
Robert Kennes, Philippe Smets
In this paper we associate with every (directed) graph G a transformation called the Mobius transformation of the graph G. The Mobius transformation of the graph (O) is of major significance for Dempster-Shafer theory of evidence. However, because it is computationally very heavy, the Mobius transformation together with Dempster's rule of combination is a major obstacle to the use of Dempster-Shafer theory for handling uncertainty in expert systems. The major contribution of this paper is the discovery of the 'fast Mobius transformations' of (O). These 'fast Mobius transformations' are the fastest algorithms for computing the Mobius transformation of (O). As an easy but useful application, we provide, via the commonality function, an algorithm for computing Dempster's rule of combination which is much faster than the usual one.
Philippe Smets
Dempster-Shafer's model aims at quantifying degrees of belief But there are so many interpretations of Dempster-Shafer's theory in the literature that it seems useful to present the various contenders in order to clarify their respective positions. We shall successively consider the classical probability model, the upper and lower probabilities model, Dempster's model, the transferable belief model, the evidentiary value model, the provability or necessity model. None of these models has received the qualification of Dempster-Shafer. In fact the transferable belief model is our interpretation not of Dempster's work but of Shafer's work as presented in his book (Shafer 1976, Smets 1988). It is a ?purified' form of Dempster-Shafer's model in which any connection with probability concept has been deleted. Any model for belief has at least two components: one static that describes our state of belief, the other dynamic that explains how to update our belief given new pieces of information. We insist on the fact that both components must be considered in order to study these models. Too many authors restrict themselves to the static component and conclude that Dempster-Shafer theory is the same as some other theory. But once the dynamic component is considered, these conclusions break down. Any comparison based only on the static component is too restricted. The dynamic component must also be considered as the originality of the models based on belief functions lies in its dynamic component.
Philippe Smets
Survey of several forms of updating, with a practical illustrative example. We study several updating (conditioning) schemes that emerge naturally from a common scenarion to provide some insights into their meaning. Updating is a subtle operation and there is no single method, no single 'good' rule. The choice of the appropriate rule must always be given due consideration. Planchet (1989) presents a mathematical survey of many rules. We focus on the practical meaning of these rules. After summarizing the several rules for conditioning, we present an illustrative example in which the various forms of conditioning can be explained.
Philippe Smets
Within the transferable belief model, positive basic belief masses can be allocated to the empty set, leading to unnormalized belief functions. The nature of these unnormalized beliefs is analyzed.
Frank Klawonn, Philippe Smets
The fundamental updating process in the transferable belief model is related to the concept of specialization and can be described by a specialization matrix. The degree of belief in the truth of a proposition is a degree of justified support. The Principle of Minimal Commitment implies that one should never give more support to the truth of a proposition than justified. We show that Dempster's rule of conditioning corresponds essentially to the least committed specialization, and that Dempster's rule of combination results essentially from commutativity requirements. The concept of generalization, dual to thc concept of specialization, is described.
Hong Xu, Yen-Teh Hsia, Philippe Smets
In this paper, we present a decision support system based on belief functions and the pignistic transformation. The system is an integration of an evidential system for belief function propagation and a valuation-based system for Bayesian decision analysis. The two subsystems are connected through the pignistic transformation. The system takes as inputs the user's "gut feelings" about a situation and suggests what, if any, are to be tested and in what order, and it does so with a user friendly interface.
Philippe Smets
Jeffrey's rule of conditioning has been proposed in order to revise a probability measure by another probability function. We generalize it within the framework of the models based on belief functions. We show that several forms of Jeffrey's conditionings can be defined that correspond to the geometrical rule of conditioning and to Dempster's rule of conditioning, respectively.
Hong Xu, Philippe Smets
In the existing evidential networks with belief functions, the relations among the variables are always represented by joint belief functions on the product space of the involved variables. In this paper, we use conditional belief functions to represent such relations in the network and show some relations of these two kinds of representations. We also present a propagation algorithm for such networks. By analyzing the properties of some special evidential networks with conditional belief functions, we show that the reasoning process can be simplified in such kinds of networks.
Philippe Smets
We construct the belief function that quantifies the agent, beliefs about which event of Q will occurred when he knows that the event is selected by a chance set-up and that the probability function associated to the chance set up is only partially known.
Hong Xu, Philippe Smets
In this paper, we present two methods to provide explanations for reasoning with belief functions in the valuation-based systems. One approach, inspired by Strat's method, is based on sensitivity analysis, but its computation is simpler thus easier to implement than Strat's. The other one is to examine the impact of evidence on the conclusion based on the measure of the information content in the evidence. We show the property of additivity for the pieces of evidence that are conditional independent within the context of the valuation-based systems. We will give an example to show how these approaches are applied in an evidential network.
Salem Benferhat, Alessandro Saffiotti, Philippe Smets
We present a new approach to dealing with default information based on the theory of belief functions. Our semantic structures, inspired by Adams' epsilon-semantics, are epsilon-belief assignments, where values committed to focal elements are either close to 0 or close to 1. We define two systems based on these structures, and relate them to other non-monotonic systems presented in the literature. We show that our second system correctly addresses the well-known problems of specificity, irrelevance, blocking of inheritance, ambiguity, and redundancy.
Philippe Smets
We present examples where the use of belief functions provided sound and elegant solutions to real life problems. These are essentially characterized by ?missing' information. The examples deal with 1) discriminant analysis using a learning set where classes are only partially known; 2) an information retrieval systems handling inter-documents relationships; 3) the combination of data from sensors competent on partially overlapping frames; 4) the determination of the number of sources in a multi-sensor environment by studying the inter-sensors contradiction. The purpose of the paper is to report on such applications where the use of belief functions provides a convenient tool to handle ?messy' data problems.
Didier Dubois, Michel Grabisch, Henri Prade et al.
The problem of assessing the value of a candidate is viewed here as a multiple combination problem. On the one hand a candidate can be evaluated according to different criteria, and on the other hand several experts are supposed to assess the value of candidates according to each criterion. Criteria are not equally important, experts are not equally competent or reliable. Moreover levels of satisfaction of criteria, or levels of confidence are only assumed to take their values in qualitative scales which are just linearly ordered. The problem is discussed within two frameworks, the transferable belief model and the qualitative possibility theory. They respectively offer a quantitative and a qualitative setting for handling the problem, providing thus a way to compare the nature of the underlying assumptions.