Genetic simulation for finite state machine identification

Identification methods (formal or simulation based), are used for logical design, test or sequential learning. Roughly, we can say that they consist of deriving an automaton model of a given sequential system from a functional description of its behavior. We present a novel identification approach based on genetic simulation. The first section offers a synthetic unified classification of the different known identification methods according to three criteria that have been extracted from their analysis. Then, the potentiality and interest of genetic simulation for identification is analyzed and a new genetic approach for functional identification is presented. Lastly we describe a computational experiment we made to validate our idea and the results we obtained. New perspectives are wide open now, particularly concerning the design, simulation and behavioral prediction of incremental and adaptive systems