Publication at SEFM 2022

A new publication has been accepted by the SEFM 2022.

Bernhard K. Aichernig, Sandra K├Ânig, Cristinel Mateis, Andrea Pferscher, Dominik Schmidt, and Martin Tappler: “Constrained Training of Recurrent Neural Networks for Automata Learning.”, In Schlinghoff, H., Chai M. (eds.) Software Engineering and Formal Methods, SEFM 2022, Berlin, Germany, September 28-30, 2022. Lecture Notes in Computer Science, vol. 13550. Springer (2022)


In this paper, we present a novel approach to learning finite automata with the help of recurrent neural networks. Our goal is not only to train a neural network that predicts the observable behavior of an automaton but also to learn its structure, including the set of states and transitions. In contrast to previous work, we constrain the training with a specific regularization term. We evaluate our approach with standard examples from the automata learning literature, but also include a case study of learning the finite-state models of real Bluetooth Low Energy protocol implementations. The results show that we can find an appropriate architecture to learn the correct automata in all considered cases.