GR2: A Hybrid Knowledge-Based System Using General Rules

Abstract

GR2 is a hybrid knowledge-based system consisting of a Multilayer Perceptron (MLP) and a rule-based system for hybrid knowledge representations and reasoning. Knowledge embedded in the trained MLP is extracted in the form of general (production) rules--a natural format of abstract knowledge representation. The rule extraction method integrates Black-box and Open-box techniques, obtaining feature salient and statistical properties of the training pattern set. The extracted general rules are quantified and selected in a rule validation process. Multiple inference facilities such as categorical reasoning, probabilistic reasoning and exceptional reasoning are performed in GR2.