Refined query inference

  • Efim B. Kinber
  • Thomas Zeugmann
Submitted Papers Inductive Inference I
Part of the Lecture Notes in Computer Science book series (LNCS, volume 397)

Abstract

We have examined, in some more detail, inference via queries restricted to a fixed number of mind changes as well as inference via queries where the finally synthesized programs may have anomalies. Thereby we could show that even questions involving only one type of quantifier may aid the learning process in two directions. First, the number of mind changes can be reduced, and second, more function classes become inferrible. On the other hand, the Theorems 6 and 15 show that the learning potential of QIMs does mainly depend on the complexity of the allowed questions measured in the number of involved quantifiers.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    Angluin, D., Learning regular sets from queries and counter-examples. Information and Computation 75, 2 (1987), 87–106.Google Scholar
  2. [2]
    Angluin, D., Learning k-term DNF formulas using queries and counter-examples. Dept. of Computer Science TR-559, Yale Univ., New Haven, CT, 1987.Google Scholar
  3. [3]
    Angluin, D., Queries and concept learning. Machine learning 2 (1988), 319–342.Google Scholar
  4. [4]
    Angluin, D., Learning with hints. Proc. First Workshop on Computational Learning Theory, Aug. 3–5. MIT, pp. 223–237.Google Scholar
  5. [5]
    Angluin, D.,and C.H. Smith, Inductive inference: theory and methods. Computing Surveys 15 (1983), 237–269.Google Scholar
  6. [6]
    Angluin, D.,and C.H. Smith, Inductive inference. In Encyclopedia of Artificial Intelligence, S. Shapiro, Ed., 1987.Google Scholar
  7. [7]
    Barzdin, Ya. M., Two theorems on the limiting synthesis of functions. In Theory of Algorithms and Programs I, (Ya. M. Barzdin, Ed.), pp. 82–88 (in russian), Latvian State Univ., 1974.Google Scholar
  8. [8]
    Case, J., and C.H. Smith, Comparison of identification criteria for machine inductive inference. Theoretical Computer Science 25, 2 (1983), 193–220.Google Scholar
  9. [9]
    Gasarch, W.I., and C.H. Smith, Learning via queries. Univ. of Maryland, Institute for Advanced Computer Studies, Dept. of Computer Science, TR-88-89.Google Scholar
  10. [10]
    Klette, R., and R. Wiehagen, Research in the theory of inductive inference by GDR-mathematiciens — a survey. Information Science 22, 149–169.Google Scholar
  11. [11]
    Osherson, D., Stob, M, and S. Weinstein, Systems that Learn. (MIT Press, Cambridge, MA 1986).Google Scholar
  12. [12]
    Rogers, H. Jr., Theory of Recursive Functions and Effective Computability. (McGraw-Hill, New York 1967).Google Scholar
  13. [13]
    Smith, C.H., The power of pluralism for automatic program synthesis., Journal of the ACM 29, 4 (1982), 1144–1165.Google Scholar
  14. [14]
    Smullyan, R.M., Theory of formal systems. Annals of Mathematical Studies 42, 7, (1962).Google Scholar
  15. [15]
    Wiehagen, R., Limes-Erkennung rekursiver Funktionen durch spezielle Strategien. Journal Inf. Processing and Cybernetics (EIK) 12 (1976), 1/2, 93–99.Google Scholar

Copyright information

© Springer-Verlag 1989

Authors and Affiliations

  • Efim B. Kinber
    • 1
  • Thomas Zeugmann
    • 2
  1. 1.Computing CentreLatvian State UniversityRigaUSSR
  2. 2.Department of MathematicsHumboldt University at BerlinBerlinGDR

Personalised recommendations