Advertisement

A thesis in inductive inference

  • Rolf Wiehagen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 543)

Abstract

Inductive inference is the theory of identifying recursive functions from examples. In [26], [27], [30] the following thesis was stated: Any class of recursive functions which is identifiable at all can always be identified by an enumeratively working strategy. Moreover, the identification can always be realized with respect to a suitable nonstandard (i.e. non-Gödel) numbering. We review some of the results which have led us to state this thesis. New results are presented concerning monotonic identification and corroborating the thesis. Some of the consequences of the thesis are discussed involving the development of the theory of inductive inference during the last decade. Problems of further investigation as well as further applications of non-Gödel numberings in inductive inference are summarized.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Angluin, D., Inductive inference of formal languages from positive data. Information and Control 45(1980) 117–135.Google Scholar
  2. [2]
    Angluin, D., Smith, C.H., Inductive inference: theory and methods. Computing surveys 15(1983) 237–269.Google Scholar
  3. [3]
    Barzdin, J.M., Complexity and frequency solution of some algorithmically unsolvable problems. Doctoral dissertation, Novosibirsk State University, 1971 (in Russian).Google Scholar
  4. [4]
    Beick, H.-R., Induktive Inferenz mit höchster Konvergenzgeschwindigkeit. Dissertation A, Humboldt-Universität Berlin, 1984.Google Scholar
  5. [5]
    Blum, L., Blum, M., Toward a mathematical theory of inductive inference. Information and Control 28(1975) 125–155.Google Scholar
  6. [6]
    Blumer, A., Ehrenfeucht, A., Haussler, D., Warmuth, M., Occam's razor. Information Processing Letters 24(1987) 377–380.Google Scholar
  7. [7]
    Board, R., Pitt, L., On the necessity of Occam algorithms. University of Illinois, 'Techn. Report UIUCDCS-R-89-1544, 1989.Google Scholar
  8. [8]
    Case, J., Smith, C., Comparison of identification criteria for machine inductive inference. Theoretical Computer Science 25(1983) 193–220.Google Scholar
  9. [9]
    Freivalds, R., On the limit synthesis of numbers of general recursive functions in various computable numberings. Sov. Math. Dokl. 15(1974) 1681–1683.Google Scholar
  10. [10]
    Freivalds, R., Kinber, E.B., Wiehagen, R., Inductive inference and computable one-one numberings. Zeitschrift für Math. Logik und Grundlagen der Mathematik 28(1982) 463–479.Google Scholar
  11. [11]
    Freivalds, R., Kinber, E.B., Wiehagen, R., Connections between identifying functionals, standardizing operations, and computable numberings. Zeitschrift für Math. Logik und Grundlagen der Mathematik 30(1984) 145–164.Google Scholar
  12. [12]
    Freivalds, R., Kinber, E.B., Wiehagen, R., Probabilistic versus deterministic inductive inference in nonstandard numberings. Zeitschrift für Math. Logik und Grundlagen der Mathematik 34(1988) 531–539.Google Scholar
  13. [13]
    Freivalds, R., Kinber, E.B., Wiehagen, R., Inductive inference from good examples. Lecture Notes in Artificial Intelligence 397(1989) 1–17.Google Scholar
  14. [14]
    Gold, E.M., Language, identification in the limit. Information and Control 10(1967) 447–474.Google Scholar
  15. [15]
    Jain, S., Sharma, A., Recursion theoretic characterizations of language learning. University of Rochester, Department of Computer Science, Techn. Report 281, 1989.Google Scholar
  16. [16]
    Jantke, K.P., Monotonic and non-monotonic inductive inference. New Generation Computing 8(1991) 349–360.Google Scholar
  17. [17]
    Jantke, K.P., Beick, H.-R., Combining postulates of naturalness in inductive inference. Elektronische Informationsverarbeitung und Kybernetik 17(1981) 465–484.Google Scholar
  18. [18]
    Klette, R., Wiehagen, R., Research in the theory of inductive inference by GDR mathematicians — a survey. Information Sciences 22(1980) 149–169.Google Scholar
  19. [19]
    Kurtz, S.A., Smith, C.H., On the role of search for learning. Proc. Workshop on Computational Learning Theory (R. Rivest, D. Haussler, M. Warmuth, Eds.), 1989, 303–311.Google Scholar
  20. [20]
    Podnieks, K.M., Comparing various concepts of function prediction, Part I in: [24], Vol. 1, 68–81; Part II in [24], Vol. 2, 33–44 (in Russian).Google Scholar
  21. [21]
    Rogers, H. Jr., Theory of recursive functions and effective computability. McGraw-Hill, New York, 1967.Google Scholar
  22. [22]
    Royer, J.S., A connotational theory of program structure. Lecture Notes in Computer Science 273(1987), 186 pp.Google Scholar
  23. [23]
    Strukturerkennung diskreter kybernetischer Systeme I, II. (R. Lindner, H. Thiele, Eds.), Seminarberichte der Sekt. Mathematik der Humboldt-Universität Berlin 82(1986), 452 S.Google Scholar
  24. [24]
    Theory of algorithms and programs. Vol. 1, 2, 3 (J.M. Barzdin, Ed.), Latvian State University Riga, 1974, 1975, 1977 (in Russian).Google Scholar
  25. [25]
    Wiehagen, R., Identification of formal languages. Lecture Notes in Computer Science 53(1977) 571–579.Google Scholar
  26. [26]
    Wiehagen, R., Zur Theorie der algorithmischen Erkennung. Dissertation B, Humboldt-Universität Berlin, 1978.Google Scholar
  27. [27]
    Wiehagen, R., Characterization problems in the theory of inductive inference. Lecture Notes in Computer Science 62(1978) 494–508.Google Scholar
  28. [28]
    Wiehagen, R., How fast is program synthesis from examples. Lecture Notes in Computer Science 215(1986) 231–239.Google Scholar
  29. [29]
    Wiehagen, R., On the complexity of program synthesis from examples, Journal of Information Processing and Cybernetics 22(1986) 305–323.Google Scholar
  30. [30]
    Wiehagen, R., Jung, H., Rekursionstheoretische Charakterisierung von erkennbaren Klassen rekursiver Funktionen. Elektronische Informationsverarbeitung und Kybernetik (EIK) 13(1977) 385–397.Google Scholar
  31. [31]
    Wiehagen, R., Liepe, W., Charakteristische Eigenschaften von erkennbaren Klassen rekursiver Funktionen. Elektronische Informationsverarbeitung und Kybernetik 12(1976) 421–438.Google Scholar
  32. [32]
    Zeugmann, T., A posteriori characterizations in inductive inference of recursive functions. Journal of Information Processing and Cybernetics 19(1983) 559–594.Google Scholar
  33. [33]
    Zeugmann, T., On the synthesis of fastest programs in inductive inference. Journal of Information Processing and Cybernetics 19(1983) 627–642.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • Rolf Wiehagen
    • 1
  1. 1.Department of InformaticsHumboldt-UniversityBerlinGermany

Personalised recommendations