Inferability of recursive real-valued functions

  • Eiju Hirowatari
  • Setsuo Arikawa
Session 2
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1316)


This paper presents a metod of inductive inference of realvalued functions from given pairs of observed data of (x,h(x)), where h is a target function to be inferred. Eac of suc observed data inevitably involves some ranges of errors, and hence it is usually represented by a pair of rational numbers sow te approximate value and te error bound, respectively. On the other hand, a real number called a recursive real number can be represented by a pair of two of rational numbers, which converges to the real number and converges to zero, respectively. These sequeces show an approximate value of te real number and an error bound at each point. Such a real number can also be represented by a sequence of closed intervals wit rational end points converges to a singleton interval with the real number as both end points.

In this paper, we propose a notion of recursive real-valued functions that can enjoy the merits of the both representations of the recursive real numbers. Then we present an algorithm which approximately infers real-valued functions from numerical data with some error bounds, and show that there exists a rich set of real-valued functions which is approximately inferable in the limit from such numerical data. We also discuss the precision of the guesses from the machine when sufficient data have not yet given.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    G. Alefeld and J. Herzberger. Introduction to Interval Computations. Academic Press, London, England, 1983.Google Scholar
  2. 2.
    K. Apsītis, R. Freivalds, and C. H. Smith. On the inductive inference of real valued functions. In Proceedings of the Eighth Annual Conference on Computational Learning Theory, pp. 170–177, 1995.Google Scholar
  3. 3.
    E.M. Gold. Language identification in the limit. Information and Control, Vol. 10, pp. 447–474, 1967.CrossRefGoogle Scholar
  4. 4.
    A. Grzegorczyk Computable fuctionals. Fundamenta Mathematicae, Vol. 42, pp. 168–202, 1955.Google Scholar
  5. 5.
    A. Grzegorczyk. On the definitions of computable real continuous functions. Fundamenta Mathematicae, Vol. 44, pp. 61–71, 1957.Google Scholar
  6. 6.
    D. Haussler. Decision theoretic generalizations of the PAC model for neural net and other learning applications. Information and Computation, Vol. 100, pp. 78–150, 1992.Google Scholar
  7. 7.
    K. Ko. On the definitions of some complexity classes of real numbers. Mathematical Systems Theory, Vol. 16, pp. 95–109, 1983.Google Scholar
  8. 8.
    K. Ko. Complexity Theory of Real Functions. Birkhäuser, 1991.Google Scholar
  9. 9.
    R.E. Moore. Interval Analysis. Prentice-Hall, 1966.Google Scholar
  10. 10.
    A. Mostowski. On computable sequences. Fundamenta Mathematicae, Vol. 44, pp. 37–51, 1957.Google Scholar
  11. 11.
    R. Péter. Recursive functions (third revised edition). Academic Press, New York and London, 1967.Google Scholar
  12. 12.
    M. B. Pour-El and J.I. Richards. Computability in Analysis and Physics. Springer Verlag, 1988.Google Scholar
  13. 13.
    H.G. Rice. Recursive real numbers. In Proceedings of the American Mathematical Society Vol. 5, pp. 784–791, 1954.Google Scholar
  14. 14.
    R.M. Robinson. Review of “R. Péter: 'Rekursive funktionen', Académiai Kiadó (Akademisher Verlag), Budapest, 1951. Journal of Symbolic Logic, Vol. 16, pp. 280–282, 1951.Google Scholar
  15. 15.
    A.M. Turing. On computable numbers, with an application to the Entscheidungsproblem. In Proceedings of the London Mathematical Society Vol. 42, pp. 230–265, 1936.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Eiju Hirowatari
    • 1
  • Setsuo Arikawa
    • 1
  1. 1.Department of InformaticsKyushu UniversityFukuokaJapan

Personalised recommendations