Abstract
We investigate two of the language classes intensively studied by the algorithmic learning theory community in the context of learning with correction queries. More precisely, we show that any pattern language can be inferred in polynomial time in length of the pattern by asking just a linear number of correction queries, and that k-reversible languages are efficiently learnable within this setting. Note that although the class of all pattern languages is learnable with membership queries, this cannot be done in polynomial time. Moreover, the class of k-reversible languages is not learnable at all using membership queries only.
The preparation of this paper was done while the first author was visiting the Department of Mathematics of Turku University, and was supported in part by the European Science Foundation (ESF) for the activity entitled ’Automata: from Mathematics to Applications’, and by the FPU Fellowship AP2004-6968 from the Spanish Ministry of Education and Science.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Angluin, D.: Finding patterns common to a set of strings (extended abstract). In: STOC 1979. Proc. 11th Annual ACM Symposium on Theory of Computing, pp. 130–141. ACM Press, New York, NY, USA (1979)
Angluin, D.: A note on the number of queries needed to identify regular languages. Information and Control 51(1), 76–87 (1981)
Angluin, D.: Inference of reversible languages. Journal of the ACM 29(3), 741–765 (1982)
Angluin, D.: Learning regular sets from queries and counterexamples. Information and Computation 75(2), 87–106 (1987)
Angluin, D.: Queries and concept learning. Machine Learning 2(4), 319–342 (1988)
Angluin, D.: Negative results for equivalence queries. Machine Learning 5(2), 121–150 (1990)
Beccera-Bonache, L., Dediu, A.H., Tîrnăucă, C.: Learning DFA from correction and equivalence queries. In: Sakakibara, Y., Kobayashi, S., Sato, K., Nishino, T., Tomita, E. (eds.) ICGI 2006. LNCS (LNAI), vol. 4201, pp. 281–292. Springer, Heidelberg (2006)
Drewes, F., Högberg, J.: Query learning of regular tree languages: How to avoid dead states. Theory of Computing Systems 40(2), 163–185 (2007)
Gold, E.M.: Language identification in the limit. Information and Control 10(5), 447–474 (1967)
Hopcroft, J.E., Ullman, J.D.: Introduction to Automata Theory, Languages, and Computation. Addison-Wesley, Reading, Massachusetts (1979)
Kearns, M., Pitt, L.: A polynomial-time algorithm for learning k-variable pattern languages from examples. In: COLT 1989. Proc. 2nd Annual Workshop on Computational Learning Theory, pp. 57–71. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (1989)
Martín-Vide, C., Mitrana, V., Păun, G. (eds.): Formal Languages and Applications. Studies in Fuzzyness and Soft Computing, vol. 148, Springer, Heidelberg (2004)
Marron, A., Ko, K.I.: Identification of pattern languages from examples and queries. Information and Computation 74(2), 91–112 (1987)
Mukouchi, Y.: Characterization of finite identification. In: Jantke, K.P. (ed.) AII 1992. LNCS, vol. 642, pp. 260–267. Springer, Heidelberg (1992)
Sakakibara, Y.: Learning context-free grammars from structural data in polynomial time. Theoretical Computer Science 76, 223–242 (1990)
Tîrnăucă, C., Kobayashi, S.: A characterization of the language classes learnable with correction queries. In: TAMC 2007. LNCS, vol. 4484, pp. 398–407. Springer, Heidelberg (2007)
Tîrnăucă, C.I., Tîrnăucă, C.: Learning regular tree languages from correction and equivalence queries. Journal of Automata, Languages and Combinatorics, Special Issue WATA, 2006 (to appear, 2007)
Valiant, L.G.: A theory of the learnable. Communications of the ACM 27(11), 1134–1142 (1984)
Yokomori, T.: Learning non-deterministic finite automata from queries and counterexamples. Machine Intelligence 13, 169–189 (1994)
Yokomori, T.: Learning two-tape automata from queries and counterexamples. Mathematical Systems Theory 29(3), 259–270 (1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tîrnăucă, C., Knuutila, T. (2007). Polynomial Time Algorithms for Learning k-Reversible Languages and Pattern Languages with Correction Queries. In: Hutter, M., Servedio, R.A., Takimoto, E. (eds) Algorithmic Learning Theory. ALT 2007. Lecture Notes in Computer Science(), vol 4754. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-75225-7_23
Download citation
DOI: https://doi.org/10.1007/978-3-540-75225-7_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-75224-0
Online ISBN: 978-3-540-75225-7
eBook Packages: Computer ScienceComputer Science (R0)