Abstract
Stochastic deterministic finite automata have been introduced and are used in a variety of settings. We report here a number of results concerning the learnability of these finite state machines. In the setting of identification in the limit with probability one, we prove that stochastic deterministic finite automata cannot be identified from only a polynomial quantity of data. If concerned with approximation results, they become Pac-learnable if the L ∞ norm is used. We also investigate queries that are sufficient for the class to be learnable.
This work was supported in part by the IST Programme of the European Community, under the Pascal Network of Excellence, IST-2002-506778. This publication only reflects the authors’ views.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Paz, A.: Introduction to probabilistic automata. Academic Press, NY (1971)
Lucas, S., Vidal, E., Amari, A., Hanlon, S., Amengual, J.C.: A comparison of syntactic and statistical techniques for off-line OCR.In: [18] ,pp.168–179
Lyngsø, R.B., Pedersen, C.N.S., Nielsen, H.: Metrics and similarity measures for hidden Markov models. In: Blaschke, C., Shatkay, H. (eds.) Linking Literature, Information, and Knowledge for Biology. LNCS, vol. 6004, pp. 178–186. Springer, Heidelberg (2010)
Mohri, M.: Finite-state transducers in language and speech processing. Computational Linguistics 23, 269–311 (1997)
Kearns, M.J., Mansour, Y., Ron, D., Rubinfeld, R., Schapire, R.E., Sellie, L.: On the learnability of discrete distributions. In: Proc. of the 25th Annual ACM Symposium on Theory of Computing, pp. 273–282 (1994)
Carrasco, R.C., Oncina, J.: Learning stochastic regular grammars by means of a state merging method. In: [18] ,pp.139–150
Ron, D., Singer, Y., Tishby, N.: On the learnability and usage of acyclic probabilistic finite automata. In: Proceedings of COLT, pp. 31–40 (1995)
Harrison, M.H.: Introduction to Formal Language Theory. Addison-Wesley Publishing Company, Inc., Reading (1978)
Angluin, D.: Identifying languages from stochastic examples. Technical Report YALEU/DCS/RR-614, Yale University (1988)
de la Higuera, C., Oncina, J.: Identification with probability one of stochastic deterministic linear languages. In: Gavaldá, R., Jantke, K.P., Takimoto, E. (eds.) ALT 2003. LNCS (LNAI), vol. 2842, pp. 134–148. Springer, Heidelberg (2003)
Pitt, L.: Inductive inference, DFA’s, and computational complexity. In: Jantke, K.P. (ed.) AII 1989. LNCS, vol. 397, pp. 18–44. Springer, Heidelberg (1989)
Valiant, L.G.: A theory of the learnable. Communications of the Association for Computing Machinery 27, 1134–1142 (1984)
Angluin, D.: Queries and concept learning. Machine Learning Journal 2, 319–342 (1987)
Bergadano, F., Varricchio, S.: Learning behaviors of automata from multiplicity and equivalence queries. SIAM Journal of Computation 25, 1268–1280 (1996)
Angluin, D.: A note on the number of queries needed to identify regular languages. Information and Control 51, 76–87 (1981)
Carrasco, R.C., Oncina, J.: Learning deterministic regular grammars from stochastic samples in polynomial time. RAIRO (Theoretical Informatics and Applications) 33, 1–20 (1999)
Carlyle, J.W., Paz, A.: Realizations by stochastic finite automata. Journal of Computation and System Sciences, 26–40 (1971)
Carrasco, R.C., Oncina, J.: Grammatical Inference and Applications. In: Carrasco, R.C., Oncina, J. (eds.) ICGI 1994. LNCS, vol. 862, Springer, Heidelberg (1994)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
de la Higuera, C., Oncina, J. (2004). Learning Stochastic Finite Automata. In: Paliouras, G., Sakakibara, Y. (eds) Grammatical Inference: Algorithms and Applications. ICGI 2004. Lecture Notes in Computer Science(), vol 3264. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30195-0_16
Download citation
DOI: https://doi.org/10.1007/978-3-540-30195-0_16
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23410-4
Online ISBN: 978-3-540-30195-0
eBook Packages: Springer Book Archive