Bulletin of Mathematical Biology

, Volume 51, Issue 6, pp 681–686 | Cite as

On limits to perception and pattern recognition

  • Colin J. Thompson
  • J. B. McGuire


We propose certain general conditions that we believe are reasonable for any pattern recognition algorithm. We find that these conditions give rise to paradoxical identification. The algorithms are incapable of distinguishing composite patterns and must be able to distinguish patterns at an atomistic level.


Input Pattern Feature Detector Composite Pattern Impossibility Theorem Pattern Recognition Algorithm 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Arrow, K. J. 1963.Social Choice and Individual Values. New York: Wiley.Google Scholar
  2. Diogenes, Laertius. 1925.Lives of Eminent Philosophers vii, 82. Harvard University Press.Google Scholar
  3. Domany, E., R. Meir and W. Kinzel. 1986.Europhys. Lett. 2, 175.Google Scholar
  4. Hopfield, J. J. 1982.Proc. natl Acad. Sci. U.S.A. 79, 2554.MathSciNetCrossRefGoogle Scholar
  5. Kelly, J. S. 1978.Arrow Impossibility Theorems. AP.Google Scholar
  6. Minsky, M. L. and S. Papert. 1969.Perceptrons. Cambridge, MA: MIT.Google Scholar
  7. Rosenblatt, F. 1961.Principles of Neurodynamics. Washington DC: Spartan.Google Scholar
  8. Rumelhart, P. E., G. E. Hinton and R. J. Williams. 1986.Nature 323, 533–536.CrossRefGoogle Scholar

Copyright information

© Society for Mathematical Biology 1989

Authors and Affiliations

  • Colin J. Thompson
    • 1
  • J. B. McGuire
    • 1
  1. 1.Institute for Theoretical PhysicsUniveristy of California, Santa BarbaraSanta BarbaraUSA

Personalised recommendations