Advertisement

Pointwise Universality of the Normal Form

  • Yaser S. Abu-Mostafa

Abstract

The problems posed here arise in the context of combinational complexity of Boolean functions whose truth tables cannot be concisely specified [2]. This class of functions arises in the study of computation and decision-making based on natural data, such as the case of pattern recognition in uncontrolled environments. The main feature of these functions is the lack of a structure that would allow an efficient systematic implementation. This leaves us with a large number of essentially unrelated cases to account for, which puts a lower bound on the complexity of these functions. However, an exhaustive solution is not necessary either, since the essential dimensionality of the data is typically far less than the actual dimensionality.

Keywords

Normal Form Boolean Function Turing Machine Truth Table Pattern Recognition System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    H. Abelson et al., “Compositional Complexity of Boolean Functions,” Discrete Appl. Math., 4, pp. 1–10 (1982).MathSciNetMATHCrossRefGoogle Scholar
  2. [2]
    Y. Abu-Mostafa, Complexity of Information Extraction, Ph.D. Thesis, Caltech, 1983.Google Scholar
  3. [3]
    Y. Abu-Mostafa, “Complexity of Random Problems,” invited paper, IEEE International Symposium on Information Theory, 1985.Google Scholar
  4. [4]
    G. Chaitin, “A Theory of Program Size Formally Identical to Information Theory,” J. Assoc. Comput. Mach., 22, pp. 329–340 (1975).MathSciNetMATHCrossRefGoogle Scholar
  5. [5]
    R. Duda and P. Hart, Pattern Classification and Scene Analysis, Wiley-Interscience, New York, 1973.MATHGoogle Scholar
  6. [6]
    Z. Kohavi, Switching and Finite Automata Theory, 2nd ed., McGraw-Hill, New York, 1978.MATHGoogle Scholar
  7. [7]
    A. Kolmogorov, “Three Approaches for Defining the Concept of Information Quantity,” Inf. Transmission, 1, pp. 3–11 (1965).MathSciNetMATHGoogle Scholar
  8. [8]
    P. Martin-Lof, “The Definition of Random Sequences,” Inf. Control, 9, pp. 602–619 (1966).MathSciNetCrossRefGoogle Scholar
  9. [9]
    R. McEliece, The Theory of Information and Coding, Addison-Wesley, Reading, MA, 1977.MATHGoogle Scholar
  10. [10]
    C. Shannon, “A Mathematical Theory of Communication,” Bell Syst. Tech. J., 28, pp. 59–98 (1949).MathSciNetGoogle Scholar
  11. [11]
    C. Shannon, “The Synthesis of Two-Terminal Switching Circuits”, Bell Syst. Tech. J., 28, pp. 59–98 (1949).MathSciNetGoogle Scholar
  12. [12]
    L. Zadeh, “Fuzzy Sets,” Inf. Control, 8, pp. 338–353 (1965).MathSciNetMATHCrossRefGoogle Scholar

Copyright information

© Springer-Verlag New York Inc. 1987

Authors and Affiliations

  • Yaser S. Abu-Mostafa
    • 1
  1. 1.California Institute of TechnologyPasadenaUSA

Personalised recommendations