Bahnsen, Fin HendrikFin HendrikBahnsenFey, GörschwinGörschwinFey2020-12-072020-12-072019-04Methoden und Beschreibungssprachen zur Modellierung und Verifikation von Schaltungen und Systemen (MBMV 2019)http://hdl.handle.net/11420/8153Statistical learning methods enable the adaptation of artificial neural networks (ANN) to complex problems. Meanwhile, formal properties can be verified on small ANNs under simplified assumptions. First we show a simple algorithm to convert neural networks into a system of equations with boundary conditions. In particular, we discuss how non-linear functions may be approximated. In experiments we study the impact of this approximation on the validity on the proof of formal guarantees.enConference PaperOther