Advertisement

Fundamental Mechanisms in Machine Learning and Inductive Inference

  • Alan W. Biermann
Part of the Springer Study Edition book series (SSE)

Abstract

While learning and inductive inference are two distinctively different phenomena, they often appear together, and therefore, it is appropriate to study them simultaneously. Learning, for the purposes of this article, will be said to occur when a system self modifies to improve its own behavior. The scenario is thus that the system operates at a given performance level at one time, experiences events of one kind or another, and self modifies with purpose to achieve a higher level of performance at a later time.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    D. Angluin and C. Smith [1983], “Inductive inference: theory and methods”, ACM Computing Surveys, Vol. 15.Google Scholar
  2. [2]
    A. Biermann and J. Feldman [1972], “On the synthesis of finite-state machines from samples of their behavior”, IEEE Trans, on Computers, Vol. C-21.Google Scholar
  3. [3]
    A. Biermann [1972], “On the inference of Turing machines from sample computations”, Artificial Intelligence, Vol. 3.Google Scholar
  4. [4]
    A. Biermann, R. Baum, and F. Petry [1975], “Speeding up the synthesis of programs from traces”, IEEE Trans. on Computers, Vol. C-24.Google Scholar
  5. [5]
    A. Biermann and R. Krishnaswamy [1976], “Constructing programs from example computations”, IEEE Trans. on Software Engineering, Vol. SE-2.Google Scholar
  6. [6]
    A. Biermann [1978], “The inference of regular LISP programs from examples”, IEEE Trans. on Systems, Man, and Cybernetics, Vol. SMC-8.Google Scholar
  7. [7]
    A. Biermann and D. Smith [1979], “A production rule mechanism for generating LISP code”, IEEE Trans. on Systems, Man, and Cybernetics, Vol. SMC-9.Google Scholar
  8. [8]
    A. Biermann, J. Fairfield, and T. Beres [1982], “Signature table systems and learning”, IEEE Transactions on Systems, Man and Cybernetics, Vol. SMC-12, No. 5.Google Scholar
  9. [9]
    A. Biermann, G. Guiho, and Y. Kodratoff, (Eds.) [1984], Automatic Program Construction Techni-quuues, Macmillan Publishing Co., N.Y.Google Scholar
  10. [10]
    J. Feldman [1972], “Some decidability results in grammatical inference”, Information and Control, Vol. 20.Google Scholar
  11. [11]
    N. Findler, Ed. [1979], Associative Networks, Academic Press, N.Y.zbMATHGoogle Scholar
  12. [12]
    P. Fink and A. Biermann [1986], “The correction of ill-formed input using history-based expectation with applications to speech understanding”, to appear.Google Scholar
  13. [13]
    K.S. Fu [1975], Syntactic Methods in Pattern Recognition, Academic Press, N.Y.Google Scholar
  14. [14]
    M. Gold [1969], “Language identification in the limit”, Information and Control, Vol. 10.Google Scholar
  15. [15]
    S. Hardy [1975], “Synthesis of LISP programs from examples”, Proc. Fourth International Joint Conf. on Artificial Intelligence. Google Scholar
  16. [16]
    J.P. Jouannaud and Y. Kodratoff [1979], “Characterization of a class of functions synthesized from examples by a Summers-like method”, Proc. Sixth International Joint Conference on Artificial Intelligence. Google Scholar
  17. [17]
    S. Mamrak and P. Amer [1978], “Estimation of run times using signature table analysis”, NBS Special Publication 500–14, Fourteenth Computing Performance Evaluation User’s Group, Boston, Mass., Oct., 1978.Google Scholar
  18. [18]
    R.S. Michalski [1980], “Pattern recognition as rule-guided inductive inference”, IEEE Trans. on Pattern Analysis and Machine Intelligence. Google Scholar
  19. [19]
    R.S. Michalski, J.G. Carbonell, T.M. Mitchell, [1983], Machine Learning, Tioga Publishing Company.CrossRefGoogle Scholar
  20. [20]
    M. Minsky, Ed. [1968], Semantic Information Processing, M.I.T. Press, Cambridge, Mass.zbMATHGoogle Scholar
  21. [21]
    M. Minsky and S. Papert [1969], Perceptrons, M.I.T. Press, Cambridge, Mass.zbMATHGoogle Scholar
  22. [22]
    N. Nilsson [1965], Learning Machines, McGraw Hill.zbMATHGoogle Scholar
  23. [23]
    C. Page [1977], “Heuristics for signature table analysis as a pattern recognition technique”, IEEE Trans. on Systems, Man, and Cybernetics, Vol. SMC-7.Google Scholar
  24. [24]
    A. Samuel [1959], “Some studies in machine learning using the game of checkers”, IBM Journal of Research and Development. Google Scholar
  25. [25]
    A. Samuel [1967], “Some studies in machine learning using the game of checkers, II”, IBM Journal of Research and Development. Google Scholar
  26. [26]
    E.Y. Shapiro [1983], Algorithmic Program Debugging, M.I.T. Press, Cambridge, Mass.Google Scholar
  27. [27]
    D. Smith [1984], “The synthesis of LISP programs from examples: a survey”, in A. Biermann, G. Guiho, Y. Kodratoff (Eds.), Automatic Program Construction Techniques, Macmillan Publishing Co., 1984.Google Scholar
  28. [28]
    M. Smith [1973], “A learning program which plays partnership dominoes”, Communications of the ACM, Vol. 16.Google Scholar
  29. [29]
    P. Summers [1977], “A methodology for LISP program construction from examples”, Journal ACM, Vol. 24.Google Scholar
  30. [30]
    T. Truscott [1979], “The Duke checker program”, Journal of Recreational Mathematics, Vol. 12.Google Scholar
  31. [31]
    L. Valiant [1984], “A theory of the learnable”, Communications of the ACM, Vol. 27.Google Scholar
  32. [32]
    D. Waterman, W. Faught, P. Klahr, S. Rosenschein, and R. Wesson [1984], “Design issues for exemplary programming”, in A Biermann, G. Guiho, Y. Kodratoff (Eds.), Automatic Program Construction Techniques, Macmillan Publishing Co., N.Y. 1984.Google Scholar
  33. [33]
    R. Wharton [1977], “Grammar enumeration and inference”, Information and Control, Vol. 33.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1987

Authors and Affiliations

  • Alan W. Biermann
    • 1
  1. 1.Duke UniversityDurhamUSA

Personalised recommendations