Classifying recursive predicates and languages

  • Rolf Wiehagen
  • Carl H. Smith
  • Thomas Zeugmann
1 Inductive Inference Theory 1.2 Inductive Inference of Formal Languages

Abstract

Our goal is to arrive at a deeper understanding of the classification problem. We study a particular collection of classification problems, the classification of recursive predicates and languages. In particular, we compare the classification of predicates and languages with the classification of arbitrary recursive functions and with learning. Moreover, we refine our investigations by introducing classification within a resource bound and establish a new hierarchy. Furthermore, we introduce a formalization of multi-classification and characterize it. Finally, we study the classification of families of languages that have attracted a lot of attention in learning theory.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Adleman, L., and Blum, M. (1991), Inductive inference and unsolvability, Journal of Symbolic Logic56, 891–900.Google Scholar
  2. Angluin, D. (1980), Inductive inference of formal languages from positive data, Information and Control45, 117–135.Google Scholar
  3. Angluin, D., and Smith, C.H. (1983), Inductive inference: theory and methods, Computing Surveys15, 237–269.Google Scholar
  4. Angluin, D., and Smith, C.H. (1987), Formal inductive inference, in “Encyclopedia of Artificial Intelligence” (St.C. Shapiro, Ed.), Vol. 1, pp. 409–418, Wiley-Interscience Publication, New York.Google Scholar
  5. Barzdin. J. (1971), Complexity and frequency solution of some algorithmically unsolvable problems, Doct. Diss., Novosibirsk, State University, (in Russian).Google Scholar
  6. Bylander, T., Allemang, D., and Tanner, M. (1991), The computational complexity of diagnosis, Artificial Intelligence49, 25–60.Google Scholar
  7. Blum, L., and Blum, M. (1975), Toward a mathematical theory of inductive inference, Information and Control28, 122–155.Google Scholar
  8. Case, J., and Smith, C.H. (1983), Comparison of identification criteria for machine inductive inference, Theoretical Computer Science25, 193–220.Google Scholar
  9. Cho, S., and Reggia, J. (1993) Multiple disorder diagnosis with adaptive competitive neural networks, Artificial Intelligence in Medicine5, 469–487.Google Scholar
  10. Duda, R., and Hart, P. (1973), “Pattern Classification and Scene Analysis,” Wiley-Interscience Publication, New York.Google Scholar
  11. Freivalds, R., Kinber, E.B., and Wiehagen, R. (1992), Convergently versus divergently incorrect hypotheses in inductive inference, GOSLER Report 05/92, January 1992, Fachbereich Mathematik und Informatik, TH Leipzig.Google Scholar
  12. Fulk, M. (1990), Prudence and other restrictions in formal language learning, Information and Computation85, 1–11.Google Scholar
  13. Freivalds, R.V., and Wiehagen, R. (1979), Inductive inference with additional information, Journal of Information Processing and Cybernetics (EIK)15, 179–184.Google Scholar
  14. Gold, M.E. (1965), Limiting recursion, Journal of Symbolic Logic30, 28–48.Google Scholar
  15. Gold, M.E. (1967), Language identification in the limit, Information and Control10, 447–474.Google Scholar
  16. Jantke, K.P., and Beick, H.R. (1981). Combining postulates of naturalness in inductive inference, Journal of Information Processing and Cybernetics (EIK)17, 465–484.Google Scholar
  17. Lange, S., and Zeugmann, T. (1992a), Learning recursive languages with bounded mind changes, GOSLER-Report 16/92, FB Mathematik und Informatik, TH Leipzig, September 1992.Google Scholar
  18. Lange, S., and Zeugmann, T. (1992b), Types of monotonic language learning and their characterization, in “Proceedings 5th Annual ACM Workshop on Computational Learning Theory,” Pittsburgh, pp. 377–390, ACM Press.Google Scholar
  19. Lange, S., and Zeugmann, T. (1993), Language learning in dependence on the space of hypotheses, in “Proceedings 6th Annual ACM Conference on Computational Learning Theory,” Santa Cruz, pp. 127–136, ACM Press.Google Scholar
  20. Lewis, H., and Papadimitriou, C. (1981), “Elements of the Theory of Computation,” Prentice-Hall, Inc., Englewood Cliffs, New Jersey.Google Scholar
  21. Machtey, M., and Young, P. (1978), “An Introduction to the General Theory of Algorithms,” North-Holland, New York.Google Scholar
  22. Michalski, R.S., Carbonell, J.G., and Mitchell, T.M. (1983), “Machine Learning,” Tioga Publishing Co., Palo Alto, CA.Google Scholar
  23. Osherson, D., Stob, M., and Weinstein, S. (1986), “Systems that Learn, An Introduction to Learning Theory for Cognitive and Computer Scientists,” MIT-Press, Cambridge, Massachusetts.Google Scholar
  24. Wiehagen, R. (1991), A thesis in inductive inference, in “Proceedings First International Workshop on Nonmonotonic and Inductive Logic,” Karlsruhe, December 1990, J. Dix, K.P. Jantke and P.H. Schmitt (Eds.), Lecture Notes in Artificial Intelligence 543, pp. 184–207, Springer-Verlag.Google Scholar
  25. Wiehagen, R., and Smith, C. (1994), Classification versus generalization, Journal of Experimental and Theoretical Artificial Intelligence, to appear.Google Scholar
  26. Zeugmann, T. (1983), A-posteriori characterizations in inductive inference of recursive functions, Journal of Information Processing and Cybernetics (EIK)19, 559–594.Google Scholar
  27. Zeugmann, T. (1988), On the power of recursive optimizers, Theoretical Computer Science62, 289–310.Google Scholar

Copyright information

© Springer-Verlag 1995

Authors and Affiliations

  • Rolf Wiehagen
    • 1
  • Carl H. Smith
    • 2
  • Thomas Zeugmann
    • 3
  1. 1.Fachbereich InformatikUniversität KaiserslauternKaiserslauternGermany
  2. 2.Department of Computer ScienceUniversity of MarylandCollege ParkUSA
  3. 3.Institut für Theoretische InformatikTH DarmstadtDarmstadtGermany
  4. 4.Research Institute of Fundamental Information ScienceKyushu University 33FukuokaJapan

Personalised recommendations