Abstract
We present efficient on-line algorithms for learning unions of a constant number of tree patterns, unions of a constant number of one-variable pattern languages, and unions of a constant number of pattern languages with fixed length substitutions. By fixed length substitutions we mean that each occurence of variable x i must be substituted by terminal strings of fixed length l(x i ). We prove that if an arbitrary unions of pattern languages with fixed length substitutions can be learned efficiently then DNFs are efficiently learnable in the mistake bound model. Since we use a reduction to Winnow, our algorithms are robust against attribute noise. Furthermore, they can be modified to handle concept drift. Also, our approach is quite general and may be applicable to learning other pattern related classes. For example, we could learn a more general pattern language class in which a penalty (i.e. weight) is assigned to each violation of the rule that a terminal symbol cannot be changed or that a pair of variable symbols, of the same variable, must be substituted by the same terminal string. An instance is positive iff the penalty incurred for violating these rules is below a given tolerable threshold.
Supported in part by NSF Grant CCR-9734940.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Andris Ambainis, Sanjay Jain, and Arun Sharma. Ordinal mind change complexity of language identification. In Computational Learning Theory: Eurocolt’ 97, pages 301–315. Springer-Verlag, 1997.
Thomas R. Amoth, Paul Cull, and Prasad Tadepalli. Exact learning of tree patterns from queries and counterexamples. In Proc. 11th Annu. Conf. on Comput. Learning Theory, pages 175–186. ACM Press, New York, NY, 1998.
Thomas R. Amoth, Paul Cull, and Prasad Tadepalli. Exact learning of unordered tree patterns from queries. In Proc. 12th Annu. Conf. on Comput. Learning Theory, pages 323–332. ACM Press, New York, NY, 1999.
D. Angluin. Finding patterns common to a set of strings. J. of Comput. Syst. Sci., 21:46–62, 1980.
D. Angluin. Inductive inference of formal languages from positive data. Inform. Control, 45(2):117–135, May 1980.
D. Angluin. Queries and concept learning. Machine Learning, 2(4):319–342, April 1988.
S. Arikawa, S. Kuhara, S. Miyano, Y. Mukouchi, A. Shinohara, and T. Shinohara. A machine discovery from amino acid sequences by decision trees over regular patterns. In Intern. Conference on Fifth Generation Computer Systems, 1992.
S. Arikawa, S. Miyano, A. Shinohara, T. Shinohara, and A. Yamamota. Algorithmic learning theory with elementary formal systems. In IEICE Trans. Inf. And Syst., volume E75-D No 4, pages 405–414, 1992.
S. Arikawa, A. Shinohara, S. Miyano, and A. Shinohara. More about learning elementary formal systems. In Nonmonotonic and Inductive Logic, Lecture Notes in Artificial Intelligence, volume 659, pages 107–117. Springer-Verlag, 1991.
H. Arimura, H. Ishizaka, T. Shinohara, and S. Otsuki. A generalization of the least general generalization. In Machine Learning, volume 13, pages 59–85. Oxford Univ. Press, 1994.
Hiroki Arimura, Hiroki Ishizaka, and Takeshi Shinohara. Learning unions of tree patterns using queries. In Proc. 6th Int. Workshop on Algorithmic Learning Theory, pages 66–79. Springer-Verlag, 1995.
Peter Auer and Manfred Warmuth. Tracking the best disjunction. In Proceedings of the 36th Annual Symposium on Foundations of Computer Science, pages 312–321. IEEE Computer Society Press, Los Alamitos, CA, 1995.
A. Bairoch. Prosite: A dictionary of sites and patterns in proteins. In Nucleic Acid Research, volume 19, pages 2241–2245, 1991.
J. M. Barzdin and R. V. Frievald. On the prediction of general recursive functions. Soviet Math. Doklady, 13:1224–1228, 1972.
C. Cardie. Empirical methods in information extraction. In AI Magazine, volume 18, pages 65–80, 1997.
Thomas Erlebach, Peter Rossmanith, Hans Stadtherr, Angelika Steger, and Thomas Zeugmann. Learning one-variable pattern languages very efficiently on average, in parallel, and by asking queries. In Algorithmic Learning Theory: ALT’ 97, pages 260–276. Springer-Verlag, 1997.
Sally A. Goldman, Stephen S. Kwek, and Stephen D. Scott. Agnostic learning of geometric patterns. In Proc. 10th Annu. Conf. on Comput. Learning Theory, pages 325–333. ACM Press, New York, NY, 1997.
C. Hua and K. Ko. A note on the pattern-finding problem. Technical Report UH-CS-84-4, Department of Computer Science, University of Houston, 1984.
O. H. Ibarra and T. Jiang. Learning regular languages from counterexamples. In Proc. 1st Annu. Workshop on Comput. Learning Theory, pages 371–385, San Mateo, CA, 1988. Morgan Kaufmann.
Sanjay Jain and Arun Sharma. Elementary formal systems, intrinsic complexity, and procrastination. In Proc. 9th Annu. Conf. on Comput. Learning Theory, pages 181–192. ACM Press, New York, NY, 1996.
K. P. Jantke. Polynomial-time inference of general pattern languages. In Proceedings of the Symposium of Theoretical Aspects of Computer Science; Lecture Notes in Computer Science, volume 166, pages 314–325. Springer, 1984.
K. P. Jantke and S. Lange. Case-based representation and learning of pattern languages. In Proc. 4th Internat. Workshop on Algorithmic Learning Theory, pages 87–100. Springer-Verlag, 1993. Lecture Notes in Artificial Intelligence 744.
C. Page Jr. and A. Frisch. Generalization and learnability: A study of constrained atoms. In Inductive Logic Programming, pages 29–61, 1992.
M. Kearns and L. Pitt. A polynomial-time algorithm for learning k-variable pattern languages from examples. In Proc. 2nd Annu. Workshop on Comput. Learning Theory, pages 57–71, San Mateo, CA, 1989. Morgan Kaufmann.
K. Ko, A. Marron, and W. Tzeng. Learnig string patterns and tree patterns from examples. abstract. In State University of New York Stony Brook, 1989.
K. Ko and W. Tzeng. Three Σ p2 -complete problems in computational learning theory. Computational Complexity, 1(3):269–310, 1991.
S. Lange and R. Wiehagen. Polynomial time inference of arbitrary pattern languages. New Generation Computing, 8:361–370, 1991.
N. Littlestone. Learning when irrelevant attributes abound: A new linear-threshold algorithm. Machine Learning, 2:285–318, 1988.
N. Littlestone. Redundant noisy attributes, attribute errors, and linear threshold learning using Winnow. In Proc. 4th Annu. Workshop on Comput. Learning Theory, pages 147–156, San Mateo, CA, 1991. Morgan Kaufmann.
N. Littlestone and M. K. Warmuth. The weighted majority algorithm. Information and Computation, 108(2):212–261, 1994.
A. Marron. Learning pattern languages from a single initial example and from queries. In Proc. 1st Annu. Workshop on Comput. Learning Theory, pages 345–358, San Mateo, CA, 1988. Morgan Kaufmann.
Satoshi Matsumoto and Ayumi Shinohara. Learning pattern languages using queries. In Computational Learning Theory: Eurocolt’ 97, pages 185–197. Springer-Verlag, 1997.
Andrew R. Mitchell. Learnability of a subclass of extended pattern languages. In Proc. 11th Annu. Conf. on Comput. Learning Theory, pages 64–71. ACM Press, New York, NY, 1998.
T. Mitchell, P. Utgoff, and R. Banerji. Learning by experimentation: Acquiring and refining problem solving heuristics. In R. Michalski, J. Carbonell, T. Mitchell eds., Machine Learning, pages 163–190. Palo Alto, CA: Tioga, 1983.
S. Miyano, A. Shinohara, and T. Shinohara. Which classes of elementary formal systems are polynomial-time learnable? In Proc. 2nd Int. Workshop on Algorithmic Learning Theory, pages 139–150. IOS Press, 1992.
R. Nix. Editing by example. In Proc. 11th ACM Symposium on Principles of Programming Languages, pages 186–195. ACM Press, 1984.
L. Pitt and M. K. Warmuth. Prediction preserving reducibility. J. of Comput. Syst. Sci., 41(3):430–467, December 1990. Special issue of the for the Third Annual Conference of Structure in Complexity Theory (Washington, DC., June 88).
Rüdiger Reischuk and Thomas Zeugmann. Learning one-variable pattern languages in linear average time. In Proc. 11th Annu. Conf. on Comput. Learning Theory, pages 198–208. ACM Press, New York, NY, 1998.
R. E. Schapire. Pattern languages are not learnable. In Proc. 3rd Annu. Workshop on Comput. Learning Theory, pages 122–129, San Mateo, CA, 1990. Morgan Kaufmann.
T. Shinohara. Polynomial time inference of extended regular pattern languages. In RIMS Symposia on Software Science and Engineering, Kyoto, Japan, pages 115–127. Springer Verlag, 1982. Lecture Notes in Computer Science 147.
T. Shinohara. Polynomial time inference of pattern languages and its applications. Proceedings, 7th IBM Symp. on Math. Foundations of Computer Science, 1982.
E. Tateishi, O. Maruyama, and S. Miyano. Extracting motifs from positive and negative sequence data. In Proc. 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 Proc. First Pacific Symposium on Biocomputing, pages 599–613. World Scientific Press, 1996.
R. Wiehagen and T. Zeugmann. Ingnoring data may be the only way to learn efficiently. Journal of Experimental and Artificial Intelligence, 6:131–144, 1994.
K. Wright. Identification of unions of languages drawn from an identifiable class. In Proc. 2nd Annu. Workshop on Comput. Learning Theory, pages 328–333. Morgan Kaufmann, 1989. (See also the correction by Motoki, Shinohara and Wright in the Proceedings of the Fourth Annual Workshop on Computational Learning Theory, page 375, 1991).
T. Zeugmann. Lange and Wiehagen’s pattern language learning algorithm: An average-case analysis with respect to its total learning time. Technical Report RIFIS-TR-CS-111, RIFIS, Kyushu University 33, 1995.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Goldman, S.A., Kwek, S.S. (1999). On Learning Unions of Pattern Languages and Tree Patterns. In: Watanabe, O., Yokomori, T. (eds) Algorithmic Learning Theory. ALT 1999. Lecture Notes in Computer Science(), vol 1720. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-46769-6_29
Download citation
DOI: https://doi.org/10.1007/3-540-46769-6_29
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66748-3
Online ISBN: 978-3-540-46769-4
eBook Packages: Springer Book Archive