Results 1 
7 of
7
Probabilistic Horn abduction and Bayesian networks
 Artificial Intelligence
, 1993
"... This paper presents a simple framework for Hornclause abduction, with probabilities associated with hypotheses. The framework incorporates assumptions about the rule base and independence assumptions amongst hypotheses. It is shown how any probabilistic knowledge representable in a discrete Bayesia ..."
Abstract

Cited by 298 (37 self)
 Add to MetaCart
This paper presents a simple framework for Hornclause abduction, with probabilities associated with hypotheses. The framework incorporates assumptions about the rule base and independence assumptions amongst hypotheses. It is shown how any probabilistic knowledge representable in a discrete Bayesian belief network can be represented in this framework. The main contribution is in finding a relationship between logical and probabilistic notions of evidential reasoning. This provides a useful representation language in its own right, providing a compromise between heuristic and epistemic adequacy. It also shows how Bayesian networks can be extended beyond a propositional language. This paper also shows how a language with only (unconditionally) independent hypotheses can represent any probabilistic knowledge, and argues that it is better to invent new hypotheses to explain dependence rather than having to worry about dependence in the language. Scholar, Canadian Institute for Advanced...
Representing Bayesian networks within probabilistic Horn abduction
 In Proc. Seventh Conf. on Uncertainty in Artificial Intelligence
, 1991
"... This paper presents a simple framework for Hornclause abduction, with probabilities associated with hypotheses. It is shown how this representation can represent any probabilistic knowledge representable in a Bayesian belief network. The main contributions are in finding a relationship between logic ..."
Abstract

Cited by 13 (4 self)
 Add to MetaCart
This paper presents a simple framework for Hornclause abduction, with probabilities associated with hypotheses. It is shown how this representation can represent any probabilistic knowledge representable in a Bayesian belief network. The main contributions are in finding a relationship between logical and probabilistic notions of evidential reasoning. This can be used as a basis for a new way to implement Bayesian Networks that allows for approximations to the value of the posterior probabilities, and also points to a way that Bayesian networks can be extended beyond a propositional language. 1
Hypothetical Reasoning In Possibilistic Logic: Basic Notions, Applications And Implementation Issues
 Proc. of the 1st Maghrebin Symp. on Programming and Systems
, 1993
"... this paper we present an extension of the ATMS, called "possibilistic ATMS" (or ÕATMS for short), where the management of uncertainty is integrated inside the basic capabilities of the ATMS. Uncertainty pervading justifications or grading assumptions is represented in the framework of possibility a ..."
Abstract

Cited by 6 (6 self)
 Add to MetaCart
this paper we present an extension of the ATMS, called "possibilistic ATMS" (or ÕATMS for short), where the management of uncertainty is integrated inside the basic capabilities of the ATMS. Uncertainty pervading justifications or grading assumptions is represented in the framework of possibility and necessity measures ([32], [16]); these measures agree with the ordinal nature of what we wish to represent (it enables us to distinguish between what is plausible and what is less plausible). The certainty of each granule in the knowledge base (represented by a clause in possibilistic logic [15]) is evaluated under the form of a lower bound of a necessity measure. This uncertainty in the deduction process is propagated by means of an extended resolution principle. Uncertainty degrees are then naturally attached to the configurations of assumptions in which a given proposition is true; one can also evaluate to what degree a given configuration of assumptions is inconsistent or compute the more or less certain consequences of a configuration of assumptions. This approach enables us to handle (*) A preliminary and short version of this paper was presented at the 1st Maghrebin Symposium Programming and Systems, Algiers, Oct. 2123, 1991. See the Proceedings pp. 153173 (available from Institute of Computer Science, UST HB, Algiers). disjunctions and negations of assumptions without particular problem. Moreover, by rankordering configurations according to the degrees attached to them, ÕATMS provides a way of limiting combinatorial explosion when using ATMS in practice. We present the basic definitions and results of possibilistic logic first. In Section 4 we give the basic definitions and functionalities of the ÕATMS, illustrated by a fault diagnosis problem previously int...
SyntaxBased Default Reasoning as Probabilistic ModelBased Diagnosis
, 1994
"... We view the syntaxbased approaches to default reasoning as a modelbased diagnosis problem, where each source giving a piece of information is considered as a component. It is formalized in the ATMS framework (each source corresponds to an assumption). We assume then that all sources are independen ..."
Abstract

Cited by 3 (0 self)
 Add to MetaCart
We view the syntaxbased approaches to default reasoning as a modelbased diagnosis problem, where each source giving a piece of information is considered as a component. It is formalized in the ATMS framework (each source corresponds to an assumption). We assume then that all sources are independent and "fail" with a very small probability. This leads to a probability assignment on the set of candidates, or equivalently on the set of consistent environments. This probability assignment induces a DempsterShafer belief function which measures the probability that a proposition can be deduced from the evidence. This belief function can be used in several different ways to define a nonmonotonic consequence relation. We study ans compare these consequence relations. The case of prioritized knowledge bases is briefly considered. 1 Introduction Syntaxbased approaches to inconsistency handling, default reasoning and belief revision have been proposed and studied in various forms (e.g. [14]...
DecisionTheoretic Diagnosis and Repair: Representational and Computational Issues
 In Proc. of the 8th International Workshop on Principles of Diagnosis (DX'97
, 1997
"... In this paper, we propose an original approach to diagnosis and repair based on label computation in ATMS, where assumptions are either usual abnormality assumptions, or repairaction assumptions, or goal assumptions. We assign probabilities to component failures and utilities to gradual goals. ..."
Abstract

Cited by 3 (3 self)
 Add to MetaCart
In this paper, we propose an original approach to diagnosis and repair based on label computation in ATMS, where assumptions are either usual abnormality assumptions, or repairaction assumptions, or goal assumptions. We assign probabilities to component failures and utilities to gradual goals. Then we give an algorithm using an original method (based on the Davis and Putnam procedure) for computing the beliefbased expected utility of a repairaction. Keywords: diagnosis and repair, abductive diagnosis, DempsterShafer theory, decision theory, ATMS.
Decision as Abduction
, 1998
"... . In this article, we describe an abductive representation of decision problems under uncertainty based on ATMS. Firstly, we extend the ATMS framework so as to include, in addition to the usual assumption symbols, preference and decision symbols. Then we show how this framework can be further extend ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
. In this article, we describe an abductive representation of decision problems under uncertainty based on ATMS. Firstly, we extend the ATMS framework so as to include, in addition to the usual assumption symbols, preference and decision symbols. Then we show how this framework can be further extended, by allowing to assign multiple (real or qualitative) values to assumption and preference symbols, for modeling gradual uncertainty and preferences, respectively. Two extensions are described, agreeing respectively with two nonclassical decision theories. 1
The Belief Calculus and Uncertain Reasoning YenTeh Hsia*
"... We formulate the DempsterShafer formalism of belief functions [Shafer 761 in the spirit of logical inference systems. Our formulation (called the belief calculus) explicitly avoids the use of settheoretic notations. As such, it serves as an alternative for the use of the DempsterShafer formalism ..."
Abstract
 Add to MetaCart
We formulate the DempsterShafer formalism of belief functions [Shafer 761 in the spirit of logical inference systems. Our formulation (called the belief calculus) explicitly avoids the use of settheoretic notations. As such, it serves as an alternative for the use of the DempsterShafer formalism for uncertain reasoning.