Efficient Induction of Finite State Automata
This addresses the challenge of efficiently learning finite state automata, which is important for applications in formal verification and pattern recognition, though it appears incremental as it builds on existing induction techniques.
The paper tackles the problem of inducing complex finite state automata from behavior samples by introducing a new algorithm based on information-theoretic principles, which reduces the search space by many orders of magnitude and outperforms existing methods in both runtime and induction quality.
This paper introduces a new algorithm for the induction if complex finite state automata from samples of behavior. The algorithm is based on information theoretic principles. The algorithm reduces the search space by many orders of magnitude over what was previously thought possible. We compare the algorithm with some existing induction techniques for finite state automata and show that the algorithm is much superior in both run time and quality of inductions.