Abstract
Inductive inference can be considered as one of the fundamental paradigms of algorithmic learning theory. We survey results recently obtained and show their impact to potential applications.
Since the main focus is put on the efficiency of learning, we also deal with postulates of naturalness and their impact to the efficiency of limit learners. In particular, we look at the learnability of the class of all pattern languages and ask whether or not one can design a learner within the paradigm of learning in the limit that is nevertheless efficient.
For achieving this goal, we deal with iterative learning and its interplay with the hypothesis spaces allowed. This interplay has also a severe impact to postulates of naturalness satisfiable by any learner.
Finally, since a limit learner is only supposed to converge in the limit, one never knows at any particular learning stage whether or not the learner did already succeed. The resulting uncertainty may be prohibitive in many applications. We survey results to resolve this problem by outlining a new learning model, called stochastic finite learning. Though pattern languages can neither be finitely inferred from positive data nor PAC-learned, our approach can be extended to a stochastic finite learner that exactly infers all pattern languages from positive data with high confidence.
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. Journal of Computer and System Sciences 21, 46–62 (1980)
Angluin, D.: Inductive inference of formal languages from positive data. Information and Control 45, 117–135 (1980)
Angluin, D., Smith, C.H.: Inductive inference: Theory and methods. Computing Surveys 15(3), 237–269 (1983)
Angluin, D., Smith, C.H.: Formal inductive inference. In: Shapiro, S.C. (ed.) Encyclopedia of Artificial Intelligence, vol. 1, pp. 409–418. Wiley-Interscience Publication, New York
Arikawa, S., Shinohara, T., Yamamoto, A.: Learning elementary formal systems. Theoretical Computer Science 95, 97–113 (1992)
Blum, L., Blum, M.: Toward a mathematical theory of inductive inference. Information and Control 28, 125–155 (1975)
Blumer, A., Ehrenfeucht, A., Haussler, D., Warmuth, M.: Learnability and the Vapnik-Chervonenkis Dimension. Journal of the ACM 36, 929–965 (1989)
Bratko, I., Muggleton, S.: Applications of inductive logic programming. Communications of the ACM (1995)
Case, J., Jain, S., Lange, S., Zeugmann, T.: Incremental Concept Learning for Bounded Data Mining. Information and Computation 152(1), 74–110 (1999)
Daley, R., Smith, C.H.: On the Complexity of Inductive Inference. Information and Control 69, 12–40 (1986)
Erlebach, T., Rossmanith, P., Stadtherr, H., Steger, A., Zeugmann, T.: Learning one-variable pattern languages very efficiently on average, in parallel, and by asking queries. Theoretical Computer Science 261(1-2), 119–156 (2001)
Gold, E.M.: Language identification in the limit. Information and Control 10, 447–474 (1967)
Goldman, S.A., Kearns, M.J., Schapire, R.E.: Exact identification of circuits using fixed points of amplification functions. SIAM Journal of Computing 22, 705–726 (1993)
Haussler, D.: Bias, version spaces and Valiant’s learning framework. In: Proc. 8th National Conference on Artificial Intelligence, pp. 564–569. Morgan Kaufmann, San Mateo (1987)
Haussler, D., Kearns, M., Littlestone, N., Warmuth, M.K.: Equivalence of models for polynomial learnability. Information and Computation 95, 129–161 (1991)
Jain, S., Osherson, D., Royer, J.S., Sharma, A.: Systems That Learn: An Introduction to Learning Theory. MIT-Press, Boston (1999)
Jiang, T., Salomaa, A., Salomaa, K., Yu, S.: Inclusion is undecidable for pattern languages. In: Lingas, A., Carlsson, S., Karlsson, R. (eds.) ICALP 1993. LNCS, vol. 700, pp. 301–312. Springer, Heidelberg (1993)
Kearns, M., Pitt, L.: A polynomial-time algorithm for learning k-variable pattern languages from examples. In: Proc. Second Annual ACM Workshop on Computational Learning Theory, pp. 57–71. Morgan Kaufmann, San Mateo (1989)
Lange, S., Wiehagen, R.: Polynomial-time inference of arbitrary pattern languages. New Generation Computing 8, 361–370 (1991)
Lange, S., Zeugmann, T.: Language learning in dependence on the space of hypotheses. In: Pitt, L. (ed.) Proc. of the 6th Annual ACM Conference on Computational Learning Theory, pp. 127–136. ACM Press, New York (1993)
Lange, S., Zeugmann, T.: Set-driven and Rearrangement-independent Learning of Recursive Languages. Mathematical Systems Theory 29, 599–634 (1996)
Lange, S., Zeugmann, T.: Incremental Learning from Positive Data. Journal of Computer and System Sciences 53, 88–103 (1996)
Lavrač, N., Džeroski, S.: Inductive Logic Programming: Techniques and Applications. Ellis Horwood (1994)
Mitchell, T.: Machine Learning. McGraw Hill, New York (1997)
Mitchell, A., Sharma, A., Scheffer, T., Stephan, F.: The VC-dimension of Subclasses of Pattern Languages. In: Watanabe, O., Yokomori, T. (eds.) ALT 1999. LNCS (LNAI), vol. 1720, pp. 93–105. Springer, Heidelberg (1999)
Miyano, S., Shinohara, A., Shinohara, T.: Polynomial-time learning of elementary formal systems. New Generation Computing 18, 217–242 (2000)
Muggleton, S.: Bayesian Inductive Logic Programming. In: Warmuth, M. (ed.) Proc. 7th Annual ACM Conference on Computational Learning Theory, pp. 3–11. ACM Press, New York (1994)
Muggleton, S., De Raedt, L.: Inductive logic programming: Theory and methods. Journal of Logic Programming 19/20, 669–679 (1994)
Nix, R.P.: Editing by examples, Yale University, Dept. Computer Science, Technical Report 280 (1983)
Osherson, D.N., Stob, M., Weinstein, S.: Systems that Learn, An Introduction to Learning Theory for Cognitive and Computer Scientists. MIT-Press, Cambridge (1986)
Pitt, L.: Inductive Inference, DFAs and Computational Complexity. In: Jantke, K.P. (ed.) AII 1989. LNCS, vol. 397, pp. 18–44. Springer, Heidelberg (1989)
Reischuk, R., Zeugmann, T.: Learning One- Variable Pattern Languages in Linear Average Time. In: Proc. 11th Annual Conference on Computational Learning Theory - COLT 1998, Madison, July 24th - 26th, pp. 198–208. ACM Press, New York (1998)
Reischuk, R., Zeugmann, T.: A Complete and Tight Average-Case Analysis of Learning Monomials. In: Meinel, C., Tison, S. (eds.) STACS 1999. LNCS, vol. 1563, pp. 414–423. Springer, Heidelberg (1999)
Reischuk, R., Zeugmann, T.: An Average-Case Optimal One-Variable Pattern Language Learner. Journal of Computer and System Sciences 60(2), 302–335 (2000)
Rogers Jr., H.: Theory of Recursive Functions and Effective Computability. McGraw–Hill, New York (1967)
Rossmanith, P., Zeugmann, T.: Stochastic Finite Learning of the Pattern Languages. Machine Learning 44(1-2), 67–91 (2001)
Patterns (The Formal Language Theory Column). EATCS Bulletin 54, 46–62 (1994)
Return to patterns (The Formal Language Theory Column). EATCS Bulletin 55, 144–157 (1994)
Shimozono, S., Shinohara, A., Shinohara, T., Miyano, S., Kuhara, S., Arikawa, S.: Knowledge acquisition from amino acid sequences by machine learning system BONSAI. Trans. Information Processing Society of Japan 35, 2009–2018 (1994)
Schapire, R.E.: Pattern languages are not learnable. In: Fulk, M.A., Case, J. (eds.) Proceedings of the Third Annual ACM Workshop on Computational Learning Theory, pp. 122–129. Morgan Kaufmann, San Mateo (1990)
Shinohara, T.: Inferring unions of two pattern languages. Bulletin of Informatics and Cybernetics 20, 83–88 (1983)
Shinohara, T.: Inductive inference of monotonic formal systems from positive data. New Generation Computing 8, 371–384 (1991)
Shinohara, T., Arikawa, S.: Pattern inference. In: Lange, S., Jantke, K.P. (eds.) GOSLER 1994. LNCS (LNAI), vol. 961, pp. 259–291. Springer, Heidelberg (1995)
Shinohara, T., Arimura, H.: Inductive inference of unbounded unions of pattern languages from positive data. In: Arikawa, S., Sharma, A.K. (eds.) ALT 1996. LNCS (LNAI), vol. 1160, pp. 256–271. Springer, Heidelberg (1996)
Smullyan, R.: Theory of Formal Systems. Annals of Mathematical Studies, Princeton, NJ, vol. (47) (1961)
Valiant, L.G.: A Theory of the Learnable. Communications of the ACM 27, 1134–1142 (1984)
Wiehagen, R.: Limes-Erkennung rekursiver Funktionen durch spezielle Strategien. Journal of Information Processing and Cybernetics (EIK) 12, 93–99 (1976)
Wiehagen, R., Zeugmann, T.: Ignoring Data may be the only Way to Learn Efficiently. Journal of Experimental and Theoretical Artificial Intelligence 6, 131–144 (1994)
Wright, K.: Identification of unions of languages drawn from an identifiable class. In: Rivest, R., Haussler, D., Warmuth, M. (eds.) Proceedings of the 2nd Workshop on Computational Learning Theory, pp. 328–333. Morgan Kaufmann, San Mateo (1989)
Zeugmann, T.: Lange and Wiehagen’s Pattern Language Learning Algorithm: An Average-case Analysis with respect to its Total Learning Time. Annals of Mathematics and Artificial Intelligence 23(1-2), 117–145 (1998)
Zeugmann, T., Lange, S.: A guided tour across the boundaries of learning recursive languages. In: Lange, S., Jantke, K.P. (eds.) GOSLER 1994. LNCS, vol. 961, pp. 190–258. Springer, Heidelberg (1995)
Zeugmann, T., Lange, S., Kapur, S.: Characterizations of monotonic and dual monotonic language learning. Information and Computation 120, 155–173 (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zeugmann, T. (2003). Can Learning in the Limit Be Done Efficiently?. In: Gavaldá, R., Jantke, K.P., Takimoto, E. (eds) Algorithmic Learning Theory. ALT 2003. Lecture Notes in Computer Science(), vol 2842. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-39624-6_5
Download citation
DOI: https://doi.org/10.1007/978-3-540-39624-6_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20291-2
Online ISBN: 978-3-540-39624-6
eBook Packages: Springer Book Archive