Advertisement

Complexity issues for vacillatory function identification

  • John Case
  • Sanjay Jain
  • Arun SharmaEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 560)

Abstract

It was previously shown by Barzdin and Podnieks that one does not increase the power of learning programs for functions by allowing learning algorithms to converge to a finite set of correct programs instead of requiring them to converge to a single correct program. In this paper we define some new, subtle, but natural concepts of mind change complexity for function learning and show that, if one bounds this complexity for learning algorithms, then, by contrast with Barzdin and Podnieks result, there are interesting and sometimes complicated tradeoffs between these complexity bounds, bounds on the number of final correct programs, and learning power.

Keywords

Inductive Inference Function Learning Correct Program Program Output Final Program 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [Ang80]
    D. Angluin. Finding patterns common to a set of strings. Journal of Computer and System Sciences, 21:46–62, 1980.CrossRefGoogle Scholar
  2. [BB75]
    L. Blum and M. Blum. Toward a mathematical theory of inductive inference. Information and Control, 28:125–155, 1975.CrossRefGoogle Scholar
  3. [BF74]
    J. A. Barzdin and R. Freivalds. Prediction and limiting synthesis of recursively enumerable classes of functions. Latvijas Valsts Univ. Zimatm. Raksti, 210:101–111, 1974.Google Scholar
  4. [Blu67]
    M. Blum. A machine independent theory of the complexity of recursive functions. Journal of the ACM, 14:322–336, 1967.CrossRefGoogle Scholar
  5. [BP73]
    J. A. Barzdin and K. Podnieks. The theory of inductive inference. In Mathematical Foundations of Computer Science, 1973.Google Scholar
  6. [Cas74]
    J. Case. Periodicity in generations of automata. Mathematical Systems Theory, 8:15–32, 1974.CrossRefGoogle Scholar
  7. [Cas88]
    J. Case. The power of vacillation. In D. Haussler and L. Pitt, editors, Proceedings of the Workshop on Computational Learning Theory, pages 133–142. Morgan Kaufmann Publishers, Inc., 1988.Google Scholar
  8. [Che81]
    K. Chen. Tradeoffs in Machine Inductive Inference. PhD thesis, SUNY at Buffalo, 1981.Google Scholar
  9. [Che82]
    K. Chen. Tradeoffs in inductive inference of nearly minimal sized programs. Information and Control, 52:68–86, 1982.CrossRefGoogle Scholar
  10. [CJS89]
    J. Case, S. Jain, and A. Sharma. Convergence to nearly minimal size grammars by vacillating learning machines. In R. Rivest, D. Haussler, and M.K. Warmuth, editors, Proceedings of the Second Annual Workshop on Computational Learning Theory, Santa Cruz, California, pages 189–199. Morgan Kaufmann Publishers, Inc., August 1989.Google Scholar
  11. [CS83]
    J. Case and C. Smith. Comparison of identification criteria for machine inductive inference. Theoretical Computer Science, 25:193–220, 1983.CrossRefGoogle Scholar
  12. [DS86]
    R. Daley and C. Smith. On the complexity of inductive inference. Information and Control, 69:12–40, 1986.CrossRefGoogle Scholar
  13. [Fre75]
    R. Freivalds. Minimal Gödel numbers and their identification in the limit. Lecture Notes in Computer Science, 32:219–225, 1975.Google Scholar
  14. [Gol67]
    E. M. Gold. Language identification in the limit. Information and Control, 10:447–474, 1967.CrossRefGoogle Scholar
  15. [Gol78]
    E. M. Gold. Complexity of automaton identification from given data. Information and Control, 37:302–320, 1978.CrossRefGoogle Scholar
  16. [JS90]
    S. Jain and A. Sharma. Program size restrictions in inductive learning. Technical Report 90-06, University of Delaware, Newark, Delaware, 1990.Google Scholar
  17. [Kin74]
    E.B. Kinber. On the synthesis in the limit of almost minimal Gödel numbers. Theory Of Algorithms and Programs, LSU, Riga, U.S.S.R., 1:221–223, 1974.Google Scholar
  18. [Kin77]
    E.B. Kinber. On limit identification of minimal Gödel numbers for functions from enumerable classes. Theory of Algorithms and Programs 3;Riga 1977, pages 35–56, 1977.Google Scholar
  19. [MY78]
    M. Machtey and P. Young. An Introduction to the General Theory of Algorithms. North Holland, New York, 1978.Google Scholar
  20. [OW82]
    D. Osherson and S. Weinstein. Criteria of language learning. Information and Control, 52:123–138, 1982.CrossRefGoogle Scholar
  21. [Rog58]
    H. Rogers. Gödel numberings of partial recursive functions. Journal of Symbolic Logic, 23:331–341, 1958.Google Scholar
  22. [Rog67]
    H. Rogers. Theory of Recursive Functions and Effective Computability. McGraw Hill, New York, 1967. Reprinted. MIT Press. 1987.Google Scholar
  23. [Wie86]
    R. Wiehagen. On the complexity of program synthesis from examples. Electronische Informationverarbeitung und Kybernetik, 22:305–323, 1986.Google Scholar
  24. [Zeu83]
    T. Zeugmann. On the synthesis of fastest programs in inductive inference. Electronische Informationverarbeitung und Kybernetik, 19:625–642, 1983.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  1. 1.Department of Computer and Information SciencesUniversity of Delaware NewarkUSA
  2. 2.Department of Computer ScienceUniv. of New South WalesSydneyAustralia

Personalised recommendations