Advertisement

Probabilistic inductive inference of indices in enumerable classes of total recursive functions

  • Inguna Greitāne
Submitted Papers Inductive Inference II
Part of the Lecture Notes in Computer Science book series (LNCS, volume 397)

Abstract

We consider identification of indices of functions in recursively enumerable classes of total recursive functions. The number of changes of the hypotheses is used as the complexity measure of the inductive inference machine (IIM).

An efectively enumerable class U of total recursive functions is constructed such that for arbitrary E>0 there is a T-numbering of U such that:
  1. 1)

    every deterministic IIM needs a linear number of changes of hypotheses to identify T-indices for functions in U;

     
  2. 2)

    there is a probabilistic IIM which identifies T-indices for function in U with probability 1-E with a constant upper bound of changes of hypotheses.

     

For arbitrarily slowly growing total recursive function g(n) and arbitrary T-numbering of the class U there is a probabilistic IIM such that for arbitrary p<1 the IIM identifies U and with probability p the number changes of hypotheses does not exceed g(n).

There is a T-numbering of U such that no probabilistic IIM can identify T-indices for functions in U with a probability p (1/2<p<1) with a constant upper bound for the number of changes of hypotheses.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Barzdin J., Freivalds R. Prediction and synthesis in the limit effectively ennumerable class of functions. — Ucheniye zapiski, Latvian State university, vol. 210, 1974, p.101–111. (Russian)Google Scholar
  2. 2.
    Barzdin J. Synthesis in the limit of T-indices. — Ucheniye zapiski, Latvian State university, vol. 210, 1974, p.112–116. (Russian).Google Scholar
  3. 3.
    Uspenskii V., Semenov A. Theory of algorithms: the principal discoveries and applications, Moscow, Nauka, 1987. (Russian).Google Scholar
  4. 4.
    Freivalds R. The capability of probabilistic algorithms of inductive inference. Semiotika i informatika, 1979, N. 12, p. 137–140. (Russian).Google Scholar
  5. 5.
    Podnieks K. Probabilistic synthesis of enumerable clases of functions. Doklady AN SSSR, 1975, v. 223, N 5. (Russian).Google Scholar
  6. 6.
    Pitt L. A characterization of probabilistic inference. Proc. FOCS Symphosium, 1984, p.485–494.Google Scholar
  7. 7.
    Rodgers H.Jr. Theory of Recursive Functions and effective Computability. MIT Press, 1987, p.64.Google Scholar
  8. 8.
    Freivalds R. Functions computable in the limit by probabilistic machines. — Lecture Notes in Computer Science, Springer, 1975, v.28, p.77–87.Google Scholar
  9. 9.
    Wiehagen R., Freivalds R., and Kinber E.B. On the power of probabilistic strategies in inductive inference. — Theoretical Computer Science, 1984, v.28, No.1/2,p.111–183.Google Scholar
  10. 10.
    Freivalds R., Kinber E.B., Wiehagen R. Probabilistic versus deterministic inductive inference in nonstandard numberings. — Zeitschrift f. Math. Logik und Grundlagen d. Math., 1988, Bd. 34, H.6, s.531–539.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1989

Authors and Affiliations

  • Inguna Greitāne
    • 1
  1. 1.Computing CenterLatvian State UniversityRigaUSSR

Personalised recommendations