Automatic Induction of DEVS Structures

Machine Learning methods seem to help for model-building in the eld of Systems Theory. In this work, we present a study on a method for automatically inducing a discrete event structure (DEVS) from descriptions of behaviours of a system. To this end, both inductive learning and DEVS formalisms have been made compatible in order to translate input data into a form usable by the inductor. Morover, the language used in classical inductive learning algorithms must be enhanced to cope with the temporal characteristics of input data.