Learning rules from the experience of an expert system using genetic algorithms

It is known that genetic algorithms are useful tools in discovering different classes of individuals or categories of them. Individuals can represent concepts, situations, etc. In this paper we show how we have used genetic algorithms to analyse the information stored in the database of the diagnostics issued by an expert system called SEQA. The purpose of this study is to automatically extract rules from the experience of the expert system in order to check the coherence and completeness of the knowledge base of SEQA. The paper explains the procedure followed to reach this objective