The efficiency of identifying timed automata and the power of clocks

We develop theory on the efficiency of identifying (learning) timed automata. In particular, we show that: (i) deterministic timed automata cannot be identified efficiently in the limit from labeled data and (ii) that one-clock deterministic timed automata can be identified efficiently in the limit from labeled data. We prove these results based on the distinguishability of these classes of timed automata. More specifically, we prove that the languages of deterministic timed automata cannot, and that one-clock deterministic timed automata can be distinguished from each other using strings in length bounded by a polynomial. In addition, we provide an algorithm that identifies one-clock deterministic timed automata efficiently from labeled data.Our results have interesting consequences for the power of clocks that are interesting also out of the scope of the identification problem.

[1]  Tao Jiang,et al.  Minimal NFA Problems are Hard , 1991, SIAM J. Comput..

[2]  Barak A. Pearlmutter,et al.  Results of the Abbadingo One DFA Learning Competition and a New Evidence-Driven State Merging Algorithm , 1998, ICGI.

[3]  T. Yokomori.  On Polynomial-Time Learnability in the Limit of Strictly Deterministic Automata , 1995, Machine Learning.

[4]  Michael Sipser,et al.  Introduction to the Theory of Computation: Preliminary Edition , 1996 .

[5]  Leonard Pitt,et al.  The minimum consistent DFA problem cannot be approximated within any polynomial , 1989, [1989] Proceedings. Structure in Complexity Theory Fourth Annual Conference.

[6]  E. Mark Gold,et al.  Language Identification in the Limit , 1967, Inf. Control..

[7]  Horst Bunke,et al.  SERIES IN MACHINE PERCEPTION AND ARTIFICIAL INTELLIGENCE , 2007 .

[8]  Alex S. Taylor,et al.  Machine intelligence , 2009, CHI.

[9]  Takashi Yokomori,et al.  Learning non-deterministic finite automata from queries and counterexamples , 1994, Machine Intelligence 13.

[10]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[11]  Thomas A. Henzinger,et al.  Event-Clock Automata: A Determinizable Class of Timed Automata , 1999, Theor. Comput. Sci..

[12]  J. Oncina,et al.  INFERRING REGULAR LANGUAGES IN POLYNOMIAL UPDATED TIME , 1992 .

[13]  Sally A. Goldman,et al.  Teaching a Smarter Learner , 1996, J. Comput. Syst. Sci..

[14]  Colin de la Higuera,et al.  Characteristic Sets for Polynomial Grammatical Inference , 1997, Machine Learning.

[15]  Michael Sipser,et al.  Introduction to the Theory of Computation , 1996, SIGA.

[16]  Bengt Jonsson,et al.  Inference of Event-Recording Automata Using Timed Decision Trees , 2006, CONCUR.

[17]  Leonard Pitt,et al.  The minimum consistent DFA problem cannot be approximated within and polynomial , 1989, STOC '89.

[18]  Cees Witteveen,et al.  An algorithm for learning real-time automata , 2007 .

[19]  Wang Yi,et al.  Uppaal in a nutshell , 1997, International Journal on Software Tools for Technology Transfer.

[20]  Paul Caspi,et al.  Timed regular expressions , 2002, JACM.

[21]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[22]  E. Mark Gold,et al.  Complexity of Automaton Identification from Given Data , 1978, Inf. Control..

[23]  Rajeev Alur,et al.  A Theory of Timed Automata , 1994, Theor. Comput. Sci..

[24]  Philippe Schnoebelen,et al.  Model Checking Timed Automata with One or Two Clocks , 2004, CONCUR.

[25]  Carl Smith.  Review of Systems that Learn (second edition) by Jain, Osherson, Royer, Sharma , 2000, SIGA.