Results 1 
7 of
7
Integrating Inconsistent Data in a Probabilistic Model
 Journal of Applied NonClassical Logics
, 2003
"... In this paper we discuss knowledge integration as a process of building a joint probability distribution from an input set of lowdimensional probability distributions starting with an initial joint probability distribution. Since the solution of the problem for a consistent input set of probabil ..."
Abstract

Cited by 7 (0 self)
 Add to MetaCart
(Show Context)
In this paper we discuss knowledge integration as a process of building a joint probability distribution from an input set of lowdimensional probability distributions starting with an initial joint probability distribution. Since the solution of the problem for a consistent input set of probability distributions is known we concentrate on a setup where the input probability distributions are inconsistent. In this case the iterative proportional tting procedure (IPFP), which converges in the consistent case, tends to come to cycles. We propose to use an algorithm, which we call GEMA (an abbreviation of Generalized Expectation Maximization Algorithm), that converges even in inconsistent case to a reasonable joint probability distribution. The important property of GEMA is that it can be eciently implemented exploiting decomposability of considered distributions.
An efficient method for probabilistic knowledge integration
 Proc. of the 20th IEEE International Conference on Tools with Artificial Intelligence
"... This paper presents an efficient method, SMOOTH, for modifying a joint probability distribution to satisfy a set of inconsistent constraints. It extends the wellknown “iterative proportional fitting procedure ” (IPFP), which only works with consistent constraints. Comparing with existing methods, ..."
Abstract

Cited by 3 (2 self)
 Add to MetaCart
(Show Context)
This paper presents an efficient method, SMOOTH, for modifying a joint probability distribution to satisfy a set of inconsistent constraints. It extends the wellknown “iterative proportional fitting procedure ” (IPFP), which only works with consistent constraints. Comparing with existing methods, SMOOTH is computationally more efficient and insensitive to data. Moreover, SMOOTH can be easily integrated with Bayesian networks for Bayes reasoning with inconsistent constraints. 1.
On combining partial and incompatible information in enegotiation and earbitration
"... The complexity of the problems to be addressed in an edemocracy framework and the variety of involved stakeholders, with different backgrounds, views and access to information sources, lead to consider the case in which enegotiation should be performed among subjects who have partial, sometimes in ..."
Abstract

Cited by 2 (1 self)
 Add to MetaCart
The complexity of the problems to be addressed in an edemocracy framework and the variety of involved stakeholders, with different backgrounds, views and access to information sources, lead to consider the case in which enegotiation should be performed among subjects who have partial, sometimes incompatible, information and can hardly be gathered to discuss issues altogether, under the supervision of a facilitator. We propose a statistical method which addresses the issue of partial and incompatible information, merging it and then using it to get a final decision, possibly in an automatic way, through the processes of enegotiation and earbitration.
Probabilistic Models In Artificial Intelligence
, 1995
"... This article is devoted to Probabilistic Models used in the field of Artificial Intelligence. A Probabilistic Model is one from possibilities for handling uncertain information in AI. In its frame integration of knowledge can be defined as building a joint probability distribution from a set of olig ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
This article is devoted to Probabilistic Models used in the field of Artificial Intelligence. A Probabilistic Model is one from possibilities for handling uncertain information in AI. In its frame integration of knowledge can be defined as building a joint probability distribution from a set of oligodimensional distributions. We can use the well known Iterative Proportional Fitting (IPF) procedure. It is proved that IPF converges if the initial distribution is uniform distribution and if the set of oligodimensional distributions is consistent, i.e. if there exists at least one distribution with the given marginals [Csis 75]. If the result distribution is decomposable then it can be effectively stored and handled so that it make possible fast computation of conditional probabilities [H'aj,Havr,Jir 92]
Integrating inconsistent data in a probabilistic model
"... ABSTRACT. In this paper we discuss the process of building a joint probability distribution from an input set of lowdimensional probability distributions. Since the solution of the problem for a consistent input set of probability distributions is known we concentrate on a setup where the input pro ..."
Abstract
 Add to MetaCart
ABSTRACT. In this paper we discuss the process of building a joint probability distribution from an input set of lowdimensional probability distributions. Since the solution of the problem for a consistent input set of probability distributions is known we concentrate on a setup where the input probability distributions are inconsistent. In this case the iterative proportional fitting procedure (IPFP), which converges in the consistent case, tends to come to cycles. We propose a new algorithm that converges even in inconsistent case. The important property of the algorithm is that it can be efficiently implemented exploiting decomposability of considered distributions.
unknown title
"... Abstract 1 This paper presents an efficient method, SMOOTH, for modifying a joint probability distribution to satisfy a set of inconsistent constraints. It extends the wellknown “iterative proportional fitting procedure ” (IPFP), which only works with consistent constraints. Comparing with existing ..."
Abstract
 Add to MetaCart
(Show Context)
Abstract 1 This paper presents an efficient method, SMOOTH, for modifying a joint probability distribution to satisfy a set of inconsistent constraints. It extends the wellknown “iterative proportional fitting procedure ” (IPFP), which only works with consistent constraints. Comparing with existing methods, SMOOTH is computationally more efficient and insensitive to data. Moreover, SMOOTH can be easily integrated with Bayesian networks