Advertisement

Changing the Inference Type – Keeping the Hypothesis Space

  • Frank Balbach
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2842)

Abstract

In inductive inference all learning takes place in hypothesis spaces. We investigate for which classes of recursive functions learnability according to an inference type \(\mathcal{I}\) implies learnability according to a different inference type \(\mathcal{J}\) within the same hypothesis space.

Several classical inference types are considered. Among FIN, CONSCP, and CP the above implication is true, for all relevant classes, independently from the hypothesis space.

On the other hand, it is proved that for many other pairs \(\mathcal{(I,J)}\) hypothesis spaces exist that allow full \(\mathcal{I}\) learning power, but limit that of \(\mathcal{J}\) to finite classes.

Only in a few cases (e. g. LIM vs. CONS) the result does depend on the actual class to be learned.

Keywords

Initial Segment Recursive Function Inductive Inference Total Function Inference Type 
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. 1.
    Angluin, D., Smith, C.: Inductive inference: theory and methods. Computing- Surveys 15, 237–269 (1983)CrossRefMathSciNetGoogle Scholar
  2. 2.
    Barzdin, J.: Inductive inference of automata, functions and programs. In: Proceedings International Congress of Math., pp. 455–460 (1974)Google Scholar
  3. 3.
    Barsdin, J.M.: Dve Teoremui o predjelnom sintjese funkzii. Teorija algorithmov i programm I 82–88, Latviiskii. Gosudarstvenyi univ., Riga (1974)Google Scholar
  4. 4.
    Barsdin, J.M., Freiwald, R.W.: Prognosirovanje i predjelnyi sinfjes effektivno peretschislimyich klassov funkzii. In: Teorija algorithmov i programm I, 101–111. Latviiskii Gosudarstvenyi universitjet, Riga, (1974)Google Scholar
  5. 5.
    Beick, H.-R.: Einige qualitative Aspekte bei der Erkennung von Klassen allgemein rekursiver Funktionen. Diplomarbeit, Humboldt-Universität, Berlin (1979)Google Scholar
  6. 6.
    Blum, M.: A machine independent theory of the complexity of recursive functions. Journal of Association for Computing Machinery 11, 322–336 (1967)Google Scholar
  7. 7.
    Blum, L., Blum, M.: Toward a Mathematical Theory of Inductive Inference. Information and Control 28, 125–155 (1975)zbMATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    Case, J., Smith, C.: Comparison of Identification Criteria for Machine Inductive Inference. Theoretical Computer Science 25, 193–220 (1983)zbMATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Freivalds, R., Kinber, E.B., Wiehagen, R.: How Inductive Inference Strategies Discover Their Errors. Information and Computation 118, 208–226 (1995)zbMATHCrossRefMathSciNetGoogle Scholar
  10. 10.
    Freivalds, R.: Inductive inference of recursive functions: Qualitative theory. In: Barzdins, J., Bjorner, D. (eds.) Baltic Computer Science. LNCS, vol. 502, pp. 77–110. Springer, Heidelberg (1991)CrossRefGoogle Scholar
  11. 11.
    Gold, E.M.: Language identification in the limit. Information and Control 10, 447–474 (1967)zbMATHCrossRefGoogle Scholar
  12. 12.
    Jantke, K.P., Beick, H.-R.: Combining Postulates of Naturalness in Inductive Inference. Elektronische Informationsverarbeitung und Kybernetik 17, 465–484 (1981)zbMATHMathSciNetGoogle Scholar
  13. 13.
    Jain, S., Osherson, D., Royer, J.S., Sharma, A.: Systems that Learn: An Introduction to Learning Theory, 2nd edn. MIT Press, Cambridge (1999)Google Scholar
  14. 14.
    Machtey, M., Young, P.: An Introduction to the General Theory of Algorithms. North-Holland, New York (1978)zbMATHGoogle Scholar
  15. 15.
    Rogers, H.: Theory of Recursive Functions and Effective Computability. McGraw– Hill, New York (1967)zbMATHGoogle Scholar
  16. 16.
    Stein, W.: Konsistentes und inkonsistentes Lernen im Limes. Dissertation, Universität Kaiserslautern (1998)Google Scholar
  17. 17.
    Stephan, F., Zeugmann, T.: Learning Classes of Approximations to Non-Recursive Functions. Theoretical Computer Science 288(2), 309–341 (2002)zbMATHCrossRefMathSciNetGoogle Scholar
  18. 18.
    Wiehagen, R.: Limes-Erkennung rekursiver Funktionen durch spezielle Strategien. Elektronische Informationsverarbeitung und Kybernetik 12(1/2), 93–99 (1976)zbMATHMathSciNetGoogle Scholar
  19. 19.
    Wiehagen, R.: Zur Theorie der algorithmischen Erkennung, Dissertation B, Sektion Mathematik, Humboldt-Universität, Berlin (1978)Google Scholar
  20. 20.
    Wiehagen, R., Zeugmann, T.: Learning and Consistency. In: Lange, S., Jantke, K.P. (eds.) GOSLER 1994. LNCS, vol. 961, pp. 1–24. Springer, Heidelberg (1995)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Frank Balbach
    • 1
  1. 1.Institut für Theoretische InformatikUniversität zu LübeckLübeckGermany

Personalised recommendations