Stratified inductive hypothesis generation

  • ZS. Szabó
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 265)


In this paper first we study the enumeration technique, as essentially the only method of the inductive inference, comparing it with best strategies. We conclude that the original enumeration strategy doesn't usually from experience: it is controlled by mistakes or of negative feedback. We define a special subclass of enumeration strategies that is called asymptotic ones. It seems that such strategies are closer to the concept of learning than the original ones. Their hypotheses are divided into subhypotheses and, because of using these, they are quicker in computing and, because of their positive feedback technique, they are more stable in working than the original ones. We define also a new inductive inference type (more exactly infinite families of identification and one of them is just the BC identification) that is called asymptotic inference showing the connection with asymptotic strategies. In this type identification is made gradually by better and better hypotheses. In this way the growth of the hypothetic knowledge, i.e. the learning, can be described in the process of identification. It seems to be useful in the practice. In this meaning even also certain non-recursive functions are approximable. We belive that the criteria of asymptotic inference are more natural requirements for intuition than the earlier ones.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Angluin, D.—Smith, C.: Inductive inference: Theory and methods. Comp.Surv. Vol. 15, No.3,(1983), 237–269.Google Scholar
  2. 2.
    Barzdin, Ja.M.: Complexity and frequency solution of some algorithmically unsolvable problems. Doctoral Dissertation, Novosibirsk State University(1971, in Russian).Google Scholar
  3. 3.
    Barzdin, Ja.M.: Two theorems on the limiting synthesis of functions. Latv.Gos.Univ.Uch.Zapiski 210, (1974, in Russian), 82–88.Google Scholar
  4. 4.
    Beick, H.R.: Induktive Inferenz mit höchster Konvergenzgeschwindigkeit. Diss.A, Humboldt-Univ. Berlin, (1984).Google Scholar
  5. 5.
    Blum, L.—Blum, M.: Toward a mathematical theory of inductive inference. Inf.Control, 28 (1975), 125–155.Google Scholar
  6. 6.
    Brainerd,W.S.— Landweber,L.H.: Theory of Computation, Wiley (1974).Google Scholar
  7. 7.
    Case, J.—Smith, C.: Comparison of identification criteria for machine inductive inference. Theor.Comput.Sci. 25,(1983), 193–220.Google Scholar
  8. 8.
    Daley, R.: On the error correcting power of pluralism in inductive inference. Theor. Comput. Sci. 24, (1983), 95–104.Google Scholar
  9. 9.
    Gergely, T.—Szabó,Zs.: Fixpoint equations as hypotheses in inductive reasoning. Conf. on “Artificial Intelligence and Inductive Inference” Held in Wendisch-Rietz, present volume, (1986).Google Scholar
  10. 10.
    Gold, E.M.: Limiting recursion. J.Symb.Logic, 30 (1965), 28–48.Google Scholar
  11. 11.
    Gold, E.M.: Language Identification in the limit. Inform.Contr. Vol. 10., no.5. (1967), 447–474.Google Scholar
  12. 12.
    Horváth,S.: Complexity of sequence encodings. FCT '77, in LNCS vol.56, Springer-Verlag (1977), 399–404.Google Scholar
  13. 13.
    Jantke,K.P.: Automatic synthesis of programs and inductive inference of functions. Proc. Int Conf. “Fundamentals of Computations Theory”, Wendish-Reitz, (1979), 219–225.Google Scholar
  14. 14.
    Jantke, K.P.—Beick, H.R.: Combining postulates of naturalness in inductive inference. Elektron. Informationsverarb. Kybern. 17 (1981), 465–484.Google Scholar
  15. 15.
    Klette, R.—Goetze, B.: Ein Normalformthorem für ∑2-Funktionen. Elektron. Informationsverarb. Kybern. 14. (1978), 251–256.Google Scholar
  16. 16.
    Klette, R.—Wiehagen, R.: Research in the theory of inductive inference by GDR mathematicians — A survey. Inf.Sci.22, (1980), 149–169.Google Scholar
  17. 17.
    Podnieks, K.M.: Comparing various concepts of function prediction, Part I. Latv. Gos. Univ. Uch. Zapiski 210, (1974, in Russian), 68–81.Google Scholar
  18. 18.
    Podnieks, K.M.: Comparing various concepts of function prediction, Part II. Latv. Gos. Univ.Uch.Zapiski 233, (1975, in Russian), 33–44.Google Scholar
  19. 19.
    Rogers, H.: Theory of Recursive Functions and Effective Computability. McGrow-Hill, New-York (1967).Google Scholar
  20. 20.
    Wiehagen, R.—Liepe, W.: Characteristische Eigenschaften von erkennbaren Klassen rekursive Functionen. Elektron. Informationsverarb. Kybern. 12 (1976), 421–438.Google Scholar
  21. 21.
    Wiehagen, R.: Characterization problems in the theory of inductive inference. LNCS vol.62, (1978), 494–508.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1987

Authors and Affiliations

  • ZS. Szabó
    • 1
  1. 1.Applied Logic LaboratoryBudapest, 112Hungary

Personalised recommendations