A Method for Implementing a Probabilistic Model as a Relational Database

TL;DR

This paper presents a method to implement probabilistic inference systems using extended relational databases, enabling the use of standard database systems for probabilistic reasoning across various applications.

Contribution

It introduces a unified framework that represents probabilistic models as generalized relational databases, facilitating probabilistic inference with standard database queries.

Findings

Probabilistic requests can be processed as relational queries.

Conventional database systems can be adapted for probabilistic reasoning.

The approach supports applications like dynamic programming and constraint propagation.

Abstract

This paper discusses a method for implementing a probabilistic inference system based on an extended relational data model. This model provides a unified approach for a variety of applications such as dynamic programming, solving sparse linear equations, and constraint propagation. In this framework, the probability model is represented as a generalized relational database. Subsequent probabilistic requests can be processed as standard relational queries. Conventional database management systems can be easily adopted for implementing such an approximate reasoning system.