A Constraint Propagation Approach to Probabilistic Reasoning

TL;DR

This paper presents a constraint propagation method for probabilistic reasoning that allows simultaneous predictive and diagnostic inference, maintaining local belief sources for stable uncertainty management.

Contribution

It introduces a novel approach combining constraint propagation with probabilistic reasoning, enabling concurrent inference processes.

Findings

Supports simultaneous predictive and diagnostic inference

Maintains local belief sources for stability

Achieves harmonious propagation to equilibrium

Abstract

The paper demonstrates that strict adherence to probability theory does not preclude the use of concurrent, self-activated constraint-propagation mechanisms for managing uncertainty. Maintaining local records of sources-of-belief allows both predictive and diagnostic inferences to be activated simultaneously and propagate harmoniously towards a stable equilibrium.