Abstract
A pattern is a finite string of constant and variable symbols. For k≥1, we denote by kμΠ the set of all patterns in which each variable symbol occurs at most k times. In particular, we abbreviate μΠ for k=1. The language L(π) of a pattern π is the set of all strings obtained by substituting any non-null constant string for each variable symbol in π. In this paper, we show that any pattern π ∈ kμΠ is exactly identifiable in O(¦ω¦k+2) time from one positive example w ∈ L(π) using ¦ω¦k+1+¦π¦k membership queries. Moreover, we introduce the notion of critical pattern, and show that the number of membership queries can be reduced to ¦ω¦+¦π¦ if the target pattern π∈μΠ is not critical. For instance, any pattern π∈μΠ whose constant parts are of length at most 3 is not critical. Finally, we show a nontrivial subclass of μΠ that is identified using membership queries only, without any initial positive example.
This author is a Research Fellow of the Japan Society for the Promotion of Science (JSPS). The author's research is partly supported by Grants-in-Aid for JSPS research fellows from the Ministry of Education, Science and Culture, Japan.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
D. Angluin. Finding patterns common to a set of strings. Journal of Computer and System Science, 21:46–62, 1980.
D. Angluin. Inductive inference of formal languages from positive data. Information and Control, 45:117–135, 1980.
D. Angluin. Learning regular sets from queries and counterexamples. Information and Computation, 75:87–106, 1987.
D. Angluin. Queries and concept learning. Machine Learning, 2:319–342, 1988.
S. Arikawa, S. Kuhara, S. Miyano, A. Shinohara and T. Shinohara. A learning algorithm for elementary formal systems and its experiments on identification of transmembrane domains. In Proceedings 25th Hawaii International Conference on System Sciences, Vol. I, pages 675–684, 1992.
H. Arimura, H. Ishizaka and T. Shinohara. Learning unions of tree patterns using queries. In Proceedings of 6th Workshop on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 997, pages 66–79, 1995.
A. Bairoch. PROSITE: A dictionary of sites and patterns in proteins. Nucleic Acids Research, 19:2241–2245, 1991.
H. Ishizaka, H. Arimura and T. Shinohara. Finding tree patterns consistent with positive and negative examples using queries. In Proceedings of 5th Workshop on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 872, pages 317–332, 1994.
M. Kearns and L. Pitt. A polynomial-time algorithm for learning k-variable pattern languages from examples. In Proceedings of the 2nd Annual Conference on Computational Learning Theory, pages 57–71, 1989.
S. Lange, J. Nessel and R. Wiehagen. Language learning from good examples. In Proceedings of 5th International Workshop on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 872, pages 423–437, 1994.
S. Lange and R. Wiehagen. Polynomial-time inference of arbitrary pattern languages. New Generation Computing, 8(4):361–370, 1991.
A. Marron. Learning pattern languages from a single initial example and from queries. In Proceedings of the first Annual Conference on Computational Learning Theory, pages 311–325, 1988.
S. Matsumoto and A. Shinohara. Learning subsequence languages. In 6th European-Japanese Seminar on Information Modelling and Knowledge Bases, 1996.
S. Miyano, A. Shinohara and T. Shinohara. Which classes of elementary formal systems are polynomial-time learnable? In Proceedings of 2nd Workshop on Algorithmic Learning Theory, pages 139–150, 1991.
H. Sakamoto. Language learning from membership queries and characteristic examples. In Proceedings of 6th International Workshop on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 997, pages 55–65. Springer-Verlag, 1995.
S. Shimozono, A. Shinohara, T. Shinohara, S. Miyano, S. Kuhara and S. Arikawa. Knowledge acquisition from amino acid sequences by machine learning system BONSAI. Transactions of Information Processing Society of Japan, 35(10):2009–2018, 1994.
A. Shinohara. Teachability in computational learning. New Generation Computing, 8(4):337–347, 1990.
T. Shinohara. Polynomial time inference of extended regular pattern languages. In RIMS Symposia on Software Science and Engineering (Lecture Notes in Computer Science 147), pages 115–127, 1982.
T. Shinohara. Polynomial time inference of pattern languages and its applications. In Proceedings 7th IBM Symp. Math. Found. Comp. Sci., pages 191–209, 1982.
T. Shinohara. Inductive inference from positive data is powerful. In Proceedings of the 3rd Annual Conference on Computational Learning Theory, pages 97–110, 1990.
E. Tateishi, O. Maruyama and S. Miyano. Extracting motifs from positive and negative sequence data. In Proceeding 13th Symposium on Theoretical Aspects of Computer Science, Lecture Notes in Computer Science 1046, pages 219–230, 1996.
E. Tateishi and S. Miyano. A greedy strategy for finding motifs from positive and negative examples. In Proceeding First Pacific Symposium on Biocomputing, pages 599–613. World Scientific Press, 1996.
L. G. Valiant. A theory of the learnable. Communications of the ACM, 27:1134–1142, 1984.
T. Zeugmann. Average case analysis of pattern language learning algorithm. In Proceedings of 5th Workshop on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 872, pages 8–9, 1994.
T. Zeugmann. Lange and Wiehagen's pattern language learning algorithm: an average-case analysis with respect to its total learing time. Technical Report RIFIS-TR-CS-111, Aplil 20, Kyushu University, 1995. (to appear in Annals of Mathematics and Artificial Intelligence).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Matsumoto, S., Shinohara, A. (1997). learning pattern languages using queries. In: Ben-David, S. (eds) Computational Learning Theory. EuroCOLT 1997. Lecture Notes in Computer Science, vol 1208. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-62685-9_16
Download citation
DOI: https://doi.org/10.1007/3-540-62685-9_16
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-62685-5
Online ISBN: 978-3-540-68431-2
eBook Packages: Springer Book Archive