Bulletin of Mathematical Biology

, Volume 51, Issue 2, pp 195–205 | Cite as

Context-dependent associations in linear distributed memories

  • Eduardo Mizraji
Article

Abstract

In this article we present a method that allows conditioning of the response of a linear distributed memory to a variable context. This method requires a system of two neural networks. The first net constructs the Kronecker product between the vector input and the vector context, and the second net supports a linear associative memory. This system is easily adaptable for different goals. We analyse here its capacity for the conditional extraction of features from a complex perceptual input, its capacity to perform quasi-logical operations (for instance, of the kind of “exclusive-or”), and its capacity to structurate a memory for temporal sequences which access is conditioned by the context. Finally, we evaluate the potential importance of the capacity to establish arbitrary contexts, for the evolution of biological cognitive systems.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Literature

  1. Anderson, J.A. 1970. “Two Models for Memory Organization Using Interacting Traces”.Math. Biosci.,8, 137–160.CrossRefGoogle Scholar
  2. — 1972. “A Simple Neural Network Generating an Interactive Memory”.Math. Biosci. 14, 197–220.MATHCrossRefGoogle Scholar
  3. — 1983. “Cognitive and Psychological Computation with Neural Models”.IEEE Trans. Systems. Man Cybernetics 13, 799–815.Google Scholar
  4. —, J. W. Silverstein, S. A. Ritz and R. S. Jones. 1977. “Distinctive Features, Categorical Perception, and Probability Learning: Some Applications of a Neural Model”.Psychol. Rev. 84, 413–451.CrossRefGoogle Scholar
  5. Ashby, W. R. 1958. “Requisite Variety and its Implications for the Control of Complex Systems”.Cybernetica 1, 83–99.MATHGoogle Scholar
  6. Bellman, R. 1960.Introduction to Matrix Analysis. New York: McGraw-Hill.MATHGoogle Scholar
  7. Changeux, J. P. and A. Danchin. 1976. “Selective Stabilization of Developing Synapses as a Mechanism for the Specification of Neuronal Networks”.Nature 264, 705–712.CrossRefGoogle Scholar
  8. Cooper, L. N. 1973. “A Possible Organization of Animal Memory and Learning.” In Proceedings of the Nobel Symposium on Collective Properties of Physical Systems, B. Lundquist and S. Lundquist (Eds) New York: Academic Press.Google Scholar
  9. Kohonen, T. 1977.Associative Memory: A System Theoretical Approach. New York: Springer.MATHGoogle Scholar
  10. Monod, J. 1967. Leçon inaugurale, Collège de France.Google Scholar
  11. — and F. Jacob. 1963. “Allosteric Proteins and Cellular Control Systems.”J. Molec. Biol. 6, 306–329.CrossRefGoogle Scholar
  12. Nass, M. M. and L. N. Cooper. 1975. “A Theory for the Development of Feature Detecting Cells in Visual Cortex”.Biol. Cybernetics 19, 1–18.CrossRefGoogle Scholar
  13. Ribchester, R. R. 1986.Molecule, Nerve and Embryo. Glasgow: Blackie.Google Scholar
  14. Rumelhart, D. E., G. E. Hinton and J. L. McClelland. 1986. “A General Framework for Parallel Distributing Processing”. InParallel Distributing Processing, D. E. Rumelhart and J. L. McClelland (Eds). Massachusetts: MIT Press.Google Scholar
  15. —— and R. J. Williams. 1986. “Learning Representations by Back-Propagating Errors”.Nature 323, 533–536.CrossRefGoogle Scholar
  16. Stone, G. O. 1986. “An Analysis of the Delta Rule and the Learning of Statistical Associations”. InParallel Distributing Processing, D. E. Rumelhart and J. L. McClelland (Eds). Massachusetts: MIT Press.Google Scholar

Copyright information

© Society for Mathematical Biology 1989

Authors and Affiliations

  • Eduardo Mizraji
    • 1
    • 2
  1. 1.Sección BiofísicaFacultad de Humanidades y CienciasMontevideoUruguay
  2. 2.Departmento de BiofísicaFacultad de MedicinaMontevideoUruguay

Personalised recommendations