Abstract
The paper develops the theory of refutable/inductive learning as a foundation of discovery science from examples. We consider refutable/inductive language learning from positive examples, some of which may be incorrect. The error or incorrectness we consider is the one described uniformly in terms of a distance over strings. We define a k-neighbor closure of a language L as the collection of strings each of which is at most k distant from some string in L. In ordinary learning paradigm, a target language is assumed to belong to a hypothesis space without any guarantee. In this paper, we allow an inference machine to infer a neighbor closure instead of the original language as an admissible approximation. We formalize such kind of learning, and give some sufficient conditions for a hypothesis space.
As its application to concrete problems, we deal with languages defined by decision trees over patterns. The problem of learning decision trees over patterns has been studied from a viewpoint of knowledge discovery for Genome information processing in the framework of PAC learning from both positive and negative examples. We investigate their learnability in the limit from neighbor examples as well as refutable learnability from complete examples, i.e., from both positive and negative examples. Furthermore, we present some procedures which plays an important role for designing efficient learning algorithms for decision trees over regular patterns.
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
D. Angluin: Finding patterns common to a set of strings, in Proceedings of the Eleventh Annual Symposium on Theory of Computing (1979) 130–141.
D. Angluin: Inductive inference of formal languages from positive data, Information and Control 45 (1980) 117–135.
S. Arikawa, S. Kuhara, S. Miyano, Y. Mukouchi, Y. Shinohara and T. Shinohara: A machine discovery from amino acid sequences by decision trees over regular patterns, New Generation Computing 11(3,4) (1993) 361–375.
H. Arimura, T. Shinohara and S. Otsuki: Finding minimal generalizations for unions of pattern languages and its application to inductive inference from positive data, in Proceedings of the Eleventh Symposium on Theoretical Aspects of Computer Science, Lecture Notes in Computer Science 775 (1994) 646–660.
J. Case and S. Jain: Synthesizing learners tolerant computable noisy data, in Proceedings of the Ninth International Conference on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 1501 (1998) 205–219.
A. Gabrielian: Pure grammars and pure languages, International Journal of Computer Mathematics 9 (1981) 3–16.
E.M. Gold: Language identification in the limit, Information and Control 10 (1967) 447–474.
R. Hamming: “Coding and Information Theory,” Prentice Hall, englewood Cliffs, NJ (1982).
S. Jain: Program synthesis in the presence of infinite number of inaccuracies, in Proceedings of the Fifth International Workshop on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 872 (1994) 333–348.
S. Jain: Learning with refutation, in Proceedings of the Ninth International Conference on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 1501 (1998) 291–305.
S. Kobayashi and T. Yokomori: On approximately identifying concept classes in the limit, in Proceedings of the Sixth International Workshop on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 997 (1995) 298–312.
S. Lange and T. Zeugmann: Types of monotonic language learning and their characterization, in Proceedings of the Fifth Annual ACMWorkshop on Computational Learning Theory (1992) 377–390.
S. Lange and P. Watson: Machine discovery in the presence of incomplete or ambiguous data, in Proceedings of the Fifth International Workshop on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 872 (1994) 438–452.
A. Lindenmayer: Developmental systems for cellular interactions, their languages and grammars, Journal of Theoretical Biology 21 (1971) 455–484.
S. Miyano: Learning theory towards Genome informatics, in Proceedings of the Fourth International Workshop on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 744 (1993) 19–36.
T. Moriyama and M. Sato: Properties of language classes with finite elasticity, in Proceedings of the Fourth International Workshop on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 744 (1993) 187–196.
T. Motoki, T. Shinohara and K. Wright: The correct definition of finite elasticity: corrigendum to identification of unions, in Proceedings of the Fourth Annual ACM Workshop on Computational Learning Theory (1991) 375–375.
Y. Mukouchi: Inductive inference of an approximate concept from positive data, in Proceedings of the Fifth International Workshop on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 872 (1994) 484–499.
Y. Mukouchi and S. Arikawa: Towards a mathematical theory of machine discovery from facts, Theoretical Computer Science 137 (1995) 53–84.
Y. Mukouchi, I. Yamaue and S. Sato: Inferring a rewriting system from examples, in Proceedings of the First International Conference on Discovery Science, Lecture Notes in Artificial Intelligence 1532 (1998) 93–104.
Y. Mukouchi: Refutable inference with a restricted target class, Mathematica Japonica 49(3) (1999) 363–372.
Y. Mukouchi and M. Sato: Language learning with a neighbor system, in Proceedings of the Third International Conference on Discovery Science, Lecture Notes in Artificial Intelligence 1967 (2000) 183–196.
Y. Mukouchi and M. Sato: Refutable language learning with a neighbor system, to appear in Theoretical Computer Science.
Y. Sakakibara and R. Siromoney: A noise model on learning sets of strings, in Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory (1992) 295–302.
R. A. Wagner and M. J. Fischer: The string-to-string correction problem, Journal of the ACM 21(1) (1974) 168–173.
M. Sato: Inductive inference of formal languages, Bulletin of Informatics and Cybernetics 27(1) (1995) 85–106.
M. Sato, Y. Mukouchi and D. Zheng: Characteristic sets for unions of regular pattern languages and compactness, in Proceedings of the Ninth International Conference on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 1501 (1998) 220–233.
M. Sato and Y. Mukouchi: Inductive inference of languages generated by regular pattern languages, in Proceedings of JSAI Meeting at Okinawa Convention Center (1999).
T. Shinohara: Polynomial time inference of pattern languages and its applications, in Proceedings of the Seventh IBM Symposium on Mathematical Foundations of Computer Sciences (1982) 191–209.
T. Shinohara: Inductive inference from negative data, Bulletin of Informatics and Cybernetics 21(3,4) (1985) 67–70.
F. Stephan: Noisy inference and oracles, in Proceedings of the Sixth International Workshop on Algorithmic Learning Theory, Lecture Notes on Artificial Intelligence 997 (1995) 185–200.
R. M. Smullyan: “Elementary Formal Systems,” Princeton University Press (1961).
M. Terada, Y. Mukouchi and M. Sato: Inductive inference of decision trees over patterns from positive examples, Transactions of IEICE J83-D-I(1) 60–67, in Japanese.
K. Wright: Identifition of unions of languages drawn from an identifile class, in Proceedings of the Second Annual ACM Workshop on Computational Learning Theory (1989) 328–333.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Sato, M., Mukouchi, Y., Terada, M. (2002). Refutable/Inductive Learning from Neighbor Examples and Its Application to Decision Trees over Patterns. In: Arikawa, S., Shinohara, A. (eds) Progress in Discovery Science. Lecture Notes in Computer Science(), vol 2281. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-45884-0_12
Download citation
DOI: https://doi.org/10.1007/3-540-45884-0_12
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-43338-5
Online ISBN: 978-3-540-45884-5
eBook Packages: Springer Book Archive