Abstract
GEX (Genetic Rule EXtraction) method described in this paper is a method of rule extraction from a trained neural network. The acquired set of rules describes the performance of a neural network solving classification problems. The extracted rules are in the form of IF - THEN. The premises standing after IF set some constrains on the neural network input values. After THEN stands a designated class. The method is based on a genetic approach. GEX consists of subpopulations evolving on islands. The number of classes existing in the classification problem solved by the neural network assigns the number of subpopulations. The details of the method are presented in the paper. The results of experiments performed on well-known benchmark data sets are shown as well.