Automated Generation of Connectionist Expert Systems for Problems Involving Noise and Redundancy

TL;DR

This paper presents a modified MACIE process that generates connectionist expert systems capable of handling noisy and redundant data by dynamically creating training examples and models.

Contribution

It introduces a novel approach to adapt the MACIE process for noisy and redundant data, enhancing expert system construction from training examples.

Findings

Successfully accommodates noisy data in expert systems

Handles redundant measurements effectively

Demonstrates improved performance on complex examples

Abstract

When creating an expert system, the most difficult and expensive task is constructing a knowledge base. This is particularly true if the problem involves noisy data and redundant measurements. This paper shows how to modify the MACIE process for generating connectionist expert systems from training examples so that it can accommodate noisy and redundant data. The basic idea is to dynamically generate appropriate training examples by constructing both a 'deep' model and a noise model for the underlying problem. The use of winner-take-all groups of variables is also discussed. These techniques are illustrated with a small example that would be very difficult for standard expert system approaches.