Reflective Inductive Inference of Recursive Functions

  • Gunter Grieser
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2533)

Abstract

In this paper, we investigate reflective inductive inference of recursive functions. A reflective IIM is a learning machine that is additionally able to assess its own competence.

First, we formalize reflective learning from arbitrary example sequences. Here, we arrive at four different types of reflection: reflection in the limit, optimistic, pessimistic and exact reflection.

Then, for learning in the limit, for consistent learning of three different types and for finite learning, we compare the learning power of reflective IIMs with each other as well as with the one of standard IIMs.

Finally, we compare reflective learning from arbitrary input sequences with reflective learning from canonical input sequences. In this context, an open question regarding total-consistent identification could be solved: it holds T-CONSaT-CONS .

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    L. Blum and M. Blum. Toward a mathematical theory of inductive inference. Inf. & Control, 28:125–155, 1975.MATHCrossRefMathSciNetGoogle Scholar
  2. [2]
    M. Blum. A machine-independent theory of the complexity of recursive functions. Journal of the ACM, 14:322–336, 1967.MATHCrossRefMathSciNetGoogle Scholar
  3. [3]
    E.M. Gold. Language identification in the limit. Inf. & Control, 10:447–474, 1967.CrossRefMATHGoogle Scholar
  4. [4]
    G. Grieser. Reflecting inductive inference machines and its improvement by therapy. In Proc. ALT’ 96, LNAI 1160, pp. 325–336, Springer 1996.Google Scholar
  5. [5]
    S. Jain. Learning with refutation. J. Comput. Syst. Sci., 57:356–365, 1998.MATHCrossRefGoogle Scholar
  6. [6]
    S. Jain, E. Kinber, R. Wiehagen, and T. Zeugmann. Learning recursive functions refutably. In Proc. ALT’ 01, LNAI 2225, pp. 283–298, Springer 2001.Google Scholar
  7. [7]
    K.P. Jantke. Reflecting and self-confident inductive inference machines. In Proc. ALT’ 95, LNAI 997, pp. 282–297, Springer 1995.Google Scholar
  8. [8]
    K.P. Jantke and H.R. Beick. Combining postulates of naturalness in inductive inference. EIK, 17(8/9):465–484, 1981.MATHMathSciNetGoogle Scholar
  9. [9]
    E.B. Kinber and T. Zeugmann. Inductive inference of almost everywhere correct programs by reliably working strategies. EIK, 21(3):91–100, 1985.MATHMathSciNetGoogle Scholar
  10. [10]
    E. Kinber and T. Zeugmann. One-sided error probabilistic inductive inference and reliable frequency identification. Inform. & Comput., 92(2):253–284, 1991.MATHCrossRefMathSciNetGoogle Scholar
  11. [11]
    S. Lange and P. Watson. Machine Discovery in the presence of incomplete or ambiguous data. In Proc. AII’ 94 and ALT’ 94, LNAI 872, pp. 438–452 Springer-Verlag 1994.Google Scholar
  12. [12]
    S. Matsumoto and A. Shinohara. Refutably probably approximately correct learning. In Proc. AII’ 94 and ALT’ 94, LNAI 872, pp. 469–483, Springer-Verlag 1994.Google Scholar
  13. [13]
    W. Merkle and F. Stephan. Refuting learning revisited. In Proc. ALT’ 01, LNAI 2225, pp. 299–314, Springer 2001.Google Scholar
  14. [14]
    E. Minicozzi. Some natural properties of strong-identification in inductive inference. Theoret. Comput. Sci., 2:345–360, 1976.MATHCrossRefMathSciNetGoogle Scholar
  15. [15]
    Y. Mukouchi and S. Arikawa. Towards a mathematical theory of machine discovery from facts. Theoret. Comput. Sci., 137(1):53–84, 1995.MATHCrossRefMathSciNetGoogle Scholar
  16. [16]
    Y. Mukouchi and M. Sato. Refutable language learning with a neighbor system. In Proc. ALT’ 01, LNAI 2225, pp. 267–282, Springer 2001.Google Scholar
  17. [17]
    H. Rogers,Jr. Theory of Recursive Functions and Effective Computability. McGraw-Hill, New York, 1967.MATHGoogle Scholar
  18. [18]
    B. A. Trakhtenbrot and J.M. Bārzdinņš. Finite Automata, Behavior and Synthesis North Holland, Amsterdam, 1973.MATHGoogle Scholar
  19. [19]
    R. Wiehagen. Limes-Erkennung rekursiver Funktionen durch spezielle Strategien. EIK, 12(1/2):93–99, 1976.MATHMathSciNetGoogle Scholar
  20. [20]
    R. Wiehagen and W. Liepe. Charakteristische Eigenschaften von erkennbaren Klassen rekursiver Funktionen. EIK, 12(8/9):421–438, 1976.MATHMathSciNetGoogle Scholar
  21. [21]
    R. Wiehagen and T. Zeugmann. Learning and consistency. In AlgorithmicL earning for Knowledge-Based Systems, LNAI 961, pp. 1–24, Springer 1995.Google Scholar
  22. [22]
    T. Zeugmann. Algorithmisches Lernen von Funktionen und Sprachen. Habilitationsschrift, Technische Hochschule Darmstadt, Fachbereich Informatik, 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Gunter Grieser
    • 1
  1. 1.Technische Universität Darmstadt, Fachbereich InformatikDarmstadtGermany

Personalised recommendations