Advertisement

Biological Cybernetics

, Volume 45, Issue 1, pp 35–41 | Cite as

A neural model for category learning

  • Douglas L. Reilly
  • Leon N. Cooper
  • Charles Elbaum
Article

Abstract

We present a general neural model for supervised learning of pattern categories which can resolve pattern classes separated by nonlinear, essentially arbitrary boundaries. The concept of a pattern class develops from storing in memory a limited number of class elements (prototypes). Associated with each prototype is a modifiable scalar weighting factor (λ) which effectively defines the threshold for categorization of an input with the class of the given prototype. Learning involves (1) commitment of prototypes to memory and (2) adjustment of the various λ factors to eliminate classification errors. In tests, the model ably defined classification boundaries that largely separated complicated pattern regions. We discuss the role which divisive inhibition might play in a possible implementation of the model by a network of neurons.

Keywords

Weighting Factor Supervise Learning Classification Error Pattern Region Pattern Category 
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. Amari, S.I.: Neural theory of association and concept-formation. Biol. Cybern. 26, 175–185 (1977)Google Scholar
  2. Anderson, J.A.: Two models for memory organization using interacting traces. Math. Biosci. 8, 137–160 (1970)Google Scholar
  3. Anderson, J.A.: A simple neural network generating an interactive memory. Math. Biosci. 14, 197–220 (1972)Google Scholar
  4. Anderson, J.A., Cooper, L.N.: Les modeles mathematiques de l'organization biologique de la memoire. Pluriscience 168–175, Encyclopaedia Universalis, Paris (1978)Google Scholar
  5. Barto, A.G., Sutton, R.S., Brouwer, P.S.: Associative search network: a reinforcement learning associative memory. Biol. Cybern. 40, 201–211 (1981)Google Scholar
  6. Blomfield, S.: Arithmetical operations performed by nerve cells. Brain Res. 69, 115–124 (1974)Google Scholar
  7. Bobrowski, L.: Rules for forming receptive fields of formal neurons during unsupervised learning processes. Biol. Cybern. 43, 23–28 (1982)Google Scholar
  8. Brooks, L.: Non-analytical concept formation and memory for instances. In: Cognition and categorization, pp. 169–211, Rosch, E., Lloyd, B. (eds.). Hillsdale, N.J.: Lawrence Erlbaum Associates 1978Google Scholar
  9. Cooper, L.N.: A possible organization of animal memory and learning. In: Proceedings of the nobel Symposium on collective properties of physical systems, Vol. 24, pp. 252–264, Lundquist, B., Lundquist, S. (eds.). London, New York: Academic Press 1973Google Scholar
  10. Cooper, L.N., Liberman, F., Oja, E.: A theory for the acquisition and loss of neuron specificity in visual cortex. Biol. Cybern. 33, 9–28 (1979)Google Scholar
  11. Cover, T.M., Hart, P.E.: Nearest neighbor pattern classification. IEEE Trans. Inform. Theor. 13, 21–27 (1967)Google Scholar
  12. Davis, T.L., Sterling, P.: Microcircuitry of cat visual cortex: classification of neurons in layer IV of area 17, and identification of the patterns of lateral geniculate input. J. Comp. Neur. 188, 599–628 (1979)Google Scholar
  13. Dean, A.F., Hess, R.F., Tolhurst, D.J.: Divisive inhibition involved in directional selectivity. J. Physiol. 308, 84p-85p (1980)Google Scholar
  14. Duda, R.O., Hart, P.E.: Pattern classification and scene analysis. New York: Wiley 1973Google Scholar
  15. Franks, J.J., Bransford, J.D.: Abstraction of visual patterns. J. Exp. Psychol. 90, 65–74 (1971)Google Scholar
  16. Grossberg, S.: Adaptive pattern classification and universal recoding. II. Feedback, expectation, olfaction, illusions. Biol. Cybern. 23, 187–202 (1976)Google Scholar
  17. Kogh, C., Poggio, T., Torre, V.: Retino-ganglion cells: a functional interpretation of dendritic morphology. Philos. Trans. R. Soc. (to be published)Google Scholar
  18. Kohonen, T.: Correlation matrix memories. IEEE Trans. Comput. 21, 353–359 (1972)Google Scholar
  19. Kohonen, T.: Associative memory—a system-theoretical approach. Berlin, Heidelberg, New York: Springer 1977Google Scholar
  20. Medin, D.L., Schaffer, M.M.: Context theory of classification learning. Psychol. Rev. 85, 207–238 (1978)Google Scholar
  21. Nass, M.M., Cooper, L.N.: A theory for the development of feature detecting cells in visual cortex. Biol. Cybern. 19, 1–18 (1975)Google Scholar
  22. Poggio, T.: A theory of synaptic interactions. In: Theoretical approaches in neurobiology, pp. 28–38, Reichardt, W., Poggio, T. (eds.). London: MIT Press 1981Google Scholar
  23. Posner, M.I., Keele, S.W.: On the genesis of abstract ideas. J. Exp. Psychol. 77, 353–363 (1968)Google Scholar
  24. Posner, M.I., Keele, S.W.: Retention of abstract ideas. J. Exp. Psychol. 83, 304–308 (1970)Google Scholar
  25. Reilly, D.L., Cooper, L.N., Elbaum, C.: An application of two learning systems to pattern recognition: handwritten characters (to be published)Google Scholar
  26. Rose, D.: On the arithmetical operation performed by inhibitory synapses onto the neuronal soma. Exp. Brain Res. 28, 221–223 (1977)Google Scholar
  27. White, E.L., Rock, M.P.: Three-dimensional aspects and synaptic relationships of a Golgi-impregnated spiny stellate cell reconstructed from serial thin sections. J. Neurocytol. 9, 615–636 (1980)Google Scholar

Copyright information

© Springer-Verlag 1982

Authors and Affiliations

  • Douglas L. Reilly
    • 1
  • Leon N. Cooper
    • 1
  • Charles Elbaum
    • 1
  1. 1.Center for Neural Science and Department of PhysicsBrown UniversityProvidenceUSA

Personalised recommendations