Mind Change Complexity of Inferring Unbounded Unions of Pattern Languages from Positive Data

  • Matthew de Brecht
  • Akihiro Yamamoto
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4264)


This paper gives a proof that the class of unbounded unions of languages of regular patterns with constant segment length bound is inferable from positive data with mind change bound between ωω and \(\omega^{\omega^{\omega}}\). We give a very tight bound on the mind change complexity based on the length of the constant segments and the size of the alphabet of the pattern languages. This is, to the authors’ knowledge, the first time a natural class of languages has been shown to be inferable with mind change complexity above ωω. The proof uses the notion of closure operators on a class of languages, and also uses the order type of well-partial-orderings to obtain a mind change bound. The inference algorithm presented can be easily applied to a wide range of classes of languages. Finally, we show an interesting connection between proof theory and mind change complexity.


  1. 1.
    Ambainis, A., Jain, S., Sharma, A.: Ordinal Mind Change Complexity of Language Identification. Theoretical Computer Science 220, 323–343 (1999)MATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Angluin, D.: Inductive Inference of Formal Languages from Positive Data. Information and Control 45, 117–135 (1980)MATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Birkhoff, G.: Lattice Theory, 3rd edn. American Mathematical Society (1967)Google Scholar
  4. 4.
    Brown, D.J., Suszko, R.: Abstract Logics. Dissertationes Mathematicae 102, 9–41 (1973)MathSciNetGoogle Scholar
  5. 5.
    Burris, S., Sankappanavar, H.P.: A Course in Universal Algebra. Springer, Heidelberg (1981)MATHGoogle Scholar
  6. 6.
    Cox, D., Little, J., O’Shea, D.: Ideals, Varieties, and Algorithms, 2nd edn. Springer, Heidelberg (1996)MATHGoogle Scholar
  7. 7.
    Friedman, H., Simpson, S.G., Smith, R.L.: Countable Algebra and Set Existence Axioms. Annals of Pure and Applied Logic 25, 141–181 (1983)MATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    Freivalds, R., Smith, C.H.: On the Role of Procrastination for Machine Learning. Information and Computation 107, 237–271 (1993)MATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Gallier, J.H.: What’s So Special About Kruskal’s Theorem and the Ordinal Γ0? A survey of some results in proof theory. Annals of Pure and Applied Logic 53, 199–260 (1991)MATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Gold, E.M.: Language Identification in the Limit. Information and Control 10, 447–474 (1967)MATHCrossRefGoogle Scholar
  11. 11.
    Hasegawa, R.: Well-ordering of Algebras and Kruskal’s Theorem. In: Sato, M., Hagiya, M., Jones, N.D. (eds.) Logic, Language and Computation. LNCS, vol. 792, pp. 133–172. Springer, Heidelberg (1994)CrossRefGoogle Scholar
  12. 12.
    Higman, G.: Ordering by Divisibility in Abstract Algebras. Proceedings of the London Mathematical Society, Third Series 2, 326–336 (1952)MATHCrossRefMathSciNetGoogle Scholar
  13. 13.
    Jain, S., Osherson, D., Royer, J.S., Sharma, A.: Systems That Learn, 2nd edn. MIT Press, Cambridge (1999)Google Scholar
  14. 14.
    Jain, S., Sharma, A.: Elementary Formal Systems, Intrinsic Complexity, and Procrastination. In: Proceedings of COLT 1996, pp. 181–192 (1996)Google Scholar
  15. 15.
    Jain, S., Sharma, A.: The Structure of Intrinsic Complexity of Learning. Journal of Symbolic Logic 62, 1187–1201 (1997)MATHCrossRefMathSciNetGoogle Scholar
  16. 16.
    Kleene, S.C.: Notations for Ordinal Numbers. Journal of Symbolic Logic 3, 150–155 (1938)MATHCrossRefGoogle Scholar
  17. 17.
    Kobayashi, S.: Approximate Identification, Finite Elasticity and Lattice Structure of Hypothesis Space. Technical Report, CSIM 96-04, Dept. of Compt. Sci. and Inform. Math., Univ. of Electro- Communications (1996)Google Scholar
  18. 18.
    Luo, W., Schulte, O.: Mind Change Efficient Learning. In: Auer, P., Meir, R. (eds.) COLT 2005. LNCS, vol. 3559, pp. 398–412. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  19. 19.
    Motoki, T., Shinohara, T., Wright, K.: The Correct Definition of Finite Elasticity: Corrigendum to Identification of Unions. In: Proceedings of COLT 1991, p. 375 (1991)Google Scholar
  20. 20.
    Mukouchi, Y.: Containment Problems for Pattern Languages. IEICE Trans. Inform. Systems E75-D, 420–425 (1992)Google Scholar
  21. 21.
    Sacks, G.E.: Higher Recursion Theory. Springer, Heidelberg (1990)MATHGoogle Scholar
  22. 22.
    Sharma, A., Stephan, F., Ventsov, Y.: Generalized Notions of Mind Change Complexity. Information and Computation 189, 235–262 (2004)MATHCrossRefMathSciNetGoogle Scholar
  23. 23.
    Shinohara, T., Arimura, H.: Inductive Inference of Unbounded Unions of Pattern Languages From Positive Data. Theoretical Computer Science 241, 191–209 (2000)MATHCrossRefMathSciNetGoogle Scholar
  24. 24.
    Simpson, S.G.: Ordinal Numbers and the Hilbert Basis Theorem. Journal of Symbolic Logic 53, 961–974 (1988)MATHCrossRefMathSciNetGoogle Scholar
  25. 25.
    Stephan, F., Ventsov, Y.: Learning Algebraic Structures from Text. Theoretical Computer Science 268, 221–273 (2001)MATHCrossRefMathSciNetGoogle Scholar
  26. 26.
    Wright, K.: Identification of Unions of Languages Drawn from an Identifiable Class. In: Proc. 2nd Workshop on Computational Learning Theory, pp. 328–333 (1989)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Matthew de Brecht
    • 1
  • Akihiro Yamamoto
    • 1
  1. 1.Graduate School of InformaticsKyoto UniversityKyotoJapan

Personalised recommendations