Abstract
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.
Similar content being viewed by others
Literature
Arrow, K. J. 1963.Social Choice and Individual Values. New York: Wiley.
Diogenes, Laertius. 1925.Lives of Eminent Philosophers vii, 82. Harvard University Press.
Domany, E., R. Meir and W. Kinzel. 1986.Europhys. Lett. 2, 175.
Hopfield, J. J. 1982.Proc. natl Acad. Sci. U.S.A. 79, 2554.
Kelly, J. S. 1978.Arrow Impossibility Theorems. AP.
Minsky, M. L. and S. Papert. 1969.Perceptrons. Cambridge, MA: MIT.
Rosenblatt, F. 1961.Principles of Neurodynamics. Washington DC: Spartan.
Rumelhart, P. E., G. E. Hinton and R. J. Williams. 1986.Nature 323, 533–536.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Thompson, C.J., McGuire, J.B. On limits to perception and pattern recognition. Bltn Mathcal Biology 51, 681–686 (1989). https://doi.org/10.1007/BF02459655
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02459655