A computational scheme for reasoning in dynamic probabilistic networks

Uncertainty in Artificial IntelligencePublished 1 January 1992

Uffe Kjærulff

Citations179

TL;DR

The scheme is viewed as a generalization of the inference methods of classical time-series analysis in the sense that it allows description of non-linear, multivariate dynamic systems with complex conditional independence structures.

Abstract

A computational scheme for reasoning about dynamic systems using (causal) probabilistic networks is presented. The scheme is based on the framework of Lauritzen and Spiegelhalter (1988), and may be viewed as a generalization of the inference methods of classical time-series analysis in the sense that it allows description of non-linear, multivariate dynamic systems with complex conditional independence structures. Further, the scheme provides a method for efficient backward smoothing and possibilities for efficient, approximate forecasting methods. The scheme has been implemented on top of the HUGIN shell.

Keywords

Computer Science

Journal of the Royal Statistical Society Series B (Statistical Methodology)Local Computations with Probabilities on Graphical Structures and Their Application to Expert Systems

3,970 Citations1988Steffen L. Lauritzen, David J. Spiegelhalter

This work exploits a range of local representations for the joint probability distribution, combined with topological changes to the original network termed 'marrying' and 'filling-in', which allows efficient algorithms for transfer between representations, providing rapid absorption and propagation of evidence.

Springer series in statisticsBayesian Forecasting and Dynamic Models

1,321 Citations1989Mike West, Jeff Harrison

SIAM Journal on ComputingAlgorithmic Aspects of Vertex Elimination on Graphs

1,188 Citations1976Donald J. Rose, Robert E. Tarjan +1 more

A graph-theoretic elimination process which is related to performing Gaussian elimination on sparse symmetric positive definite systems of linear equations is considered, and it is conjecture that the problem of finding a minimum ordering is NP-complete.

Computational IntelligenceA model for reasoning about persistence and causation

999 Citations1989Thomas Dean, Keiji Kanazawa

A model of causal reasoning that accounts for knowledge concerning cause‐and‐effect relationships and knowledge concerning the tendency for propositions to persist or not as a function of time passing is described.

NetworksIndependence properties of directed markov fields

521 Citations1990Steffen L. Lauritzen, A. P. Dawid +2 more

A criterion for conditional independence of two groups of variables given a third is given and named as the directed, global Markov property and it is argued that this criterion is easy to use, it is sharper than that given by Kiiveri, Speed, and Carlin and equivalent to that of Pearl.

Elsevier eBooksA GRAPH-THEORETIC STUDY OF THE NUMERICAL SOLUTION OF SPARSE POSITIVE DEFINITE SYSTEMS OF LINEAR EQUATIONS

428 Citations1972Donald J. Rose

By following the formulation of elimination as a combinatorial process a considerable insight into the elimination process by studying the evolution of the cycle structure and the vertex-separator, or cut-set, structure of a graph under elimination can be gained.

Uncertainty in Artificial IntelligenceDynamic Network Models for Forecasting

198 Citations1992Paul Dagum, Adam Galper +1 more

The dynamic network model (DNM) is presented and methods for constructing, refining, and performing inference with this representation of temporal probabilistic knowledge are described, which extends static belief-network models to more general dynamic forecasting models.

Machine intelligence and pattern recognitionProbabilistic Reasoning in Predictive Expert Systems

126 Citations1986David J. Spiegelhalter

Techniques in developing a coherent Probabilistic reasoning system are illustrated with reference to a simplified example and possible limitations of a formal probabilistic approach are discussed.

Statistics and ComputingOptimal decomposition of probabilistic networks by simulated annealing

97 Citations1992Uffe Kjærulff

This paper investigates the applicability of a Monte Carlo technique known as ‘simulated annealing’ to achieve optimum or sub-optimum decompositions of probabilistic networks under bounded resources and proves that cost-function changes can be computed locally.

Lecture notes in medical informaticsA Model-Based Approach to Insulin Adjustment

86 Citations1991Steen Andreassen, Roman Hovorka +3 more

A differential equation model of carbohydrate metabolism was implemented in the form of a causal probabilistic network that permitted explicit represen-tations of the uncertainties associated with model based predictions of 24-hour blood glucose profiles.