Skip to main content
SpringerLink
Log in

Neural theory of association and concept-formation

  • Published:
Biological Cybernetics Aims and scope Submit manuscript

Abstract

The present paper looks for possible neural mechanism underlying such high-level brain functioning as association and concept-formation. Primitive neural models of association and concept-formation are presented, which will elucidate the distributed and multiply superposed manner of retaining knowledge in the brain. The models are subject to two rules of self-organization of synaptic weights, orthogonal and covariance learning. The convergence of self-organization is proved, and the characteristics of these learning rules are shown. The performances, especially the noise immunity, of the association net and concept-formation net are analyzed.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Albert, A.: Regression and the Moore-Penrose pseudoinverse. New York Academic Press 1972

    Google Scholar 

  • Amari, S.: Characteristics of randomly connected threshold element networks and network systems. Proc. IEEE 59, 35–47 (1971)

    Google Scholar 

  • Amari, S.: Learning patterns and pattern sequences by self-organizing nets of threshold elements. IEEE Trans. Comp. C-21, 1197–1206 (1972a)

    Google Scholar 

  • Amari, S.: Characteristics of random nets of analog neuron-like elements. IEEE Trans. on Systems, Man, and Cybernetics SMC-2, 643–657 (1972b)

    Google Scholar 

  • Amari, S.: A method of statistical neurodynamics. Kybernetik 14, 201–215 (1974a)

    Google Scholar 

  • Amari, S.: A mathematical theory of nerve nets. In: Kotani, M. (Ed.): Advances in biophysics, Vol. 6, pp. 75–120. Tokyo: University Press 1974b

    Google Scholar 

  • Amari, S.: Homogeneous nets of neuron-like elements. Biol. Cybernetics 17, 211–220 (1975)

    Google Scholar 

  • Amari, S.: Dynamics of pattern formation in lateral-inhibition type neural fields. To be published (1977a)

  • Amari, S.: A mathematical approach to neural systems. In: Arbib, M. A., Metzler, J. (Eds.): Systems neuroscience. I. New York: Academic Press 1977b

    Google Scholar 

  • Amari, S., Yoshida, K., Kanatani, K.: Mathematical foundation of statistical neurodynamics. SIAM J. Appl. Math. 33 (1977)

  • Anderson, J. A.: A simple neural networks generating interactive memory. Math. Biosc. 14, 197–220 (1972)

    Google Scholar 

  • Caianiello, E. R.: Outline of a theory of thought processes and thinking machines. J. theor. Biol. 1, 204–235 (1961)

    Google Scholar 

  • Grossberg, S.: Onlearning, information lateral inhibition, and transmitters. Math. Biosc. 4, 255–310 (1969)

    Google Scholar 

  • Hebb D. O.: The organization of behavior. New York: Wiley 1949

    Google Scholar 

  • Kohonen, T.: Correlation matrix memories. IEEE Trans. Comp. C-21, 353–359 (1972)

    Google Scholar 

  • Kohonen, T.: An adaptive associative memory principle. IEEE Trans. Comp. C-23, 444–445 (1974)

    Google Scholar 

  • Kohonen, T., Oja, E.: Fast adaptive formation pf orthogonalizing filters and associative memory in recurrent networks of neuron-like elements. Biol. Cybernetics 21, 85–95 (1976)

    Google Scholar 

  • Malsburg von der, C.: Self-organization of orientation sensitive cells in the striate cortex. Kybernetik 14, 85–100 (1973)

    Google Scholar 

  • Nakano, K.: Associatron—a model of associative memory. IEEE Trans.on Systems, Man, and Cybernetics SMC-2, 380–388 (1972)

    Google Scholar 

  • Pfaffelhuber, E.: Correlation memory models—a first approximation in a general learning scheme. Biol. Cybernetics 18, 217–223 (1975)

    Google Scholar 

  • Rosenblatt, F.: Principles of Neurodynamics. Washington: Spartan 1961

    Google Scholar 

  • Spinelli, N.: OCCAM: a computer model for a content-addressable memory in the central nervous systems. Biology of memory 293–306. New York: Academic Press 1970

    Google Scholar 

  • Uesaka, Y., Ozeki, K.: Some properties of association-type memories. JIEECE of Japan (in Japanese), 55-D, 323–330 (1972)

    Google Scholar 

  • Wasan, M. T.: Stochastic approximation. Cambridge: University Press 1969

    Google Scholar 

  • Wigström, H.: A neuron model with learning capability and its relation to mechanism of association. Kybernetik 12, 204–215 (1973)

    Google Scholar 

  • Willshaw, D. J., Longuet-Higgins, H. C.: The holophone—recent developments. In: Metzler, B., Michie, D. (Eds.). Machine intelligence, Vol. 4, pp. 349–357. Edinburgh: University Press 1969

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. University of Tokyo, Tokyo, Japan

    S.-I. Amari

  2. Center for Systems Neuroscience, University of Massachusetts, Amherst, MA, USA

    S.-I. Amari

Authors
  1. S.-I. Amari
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

This research was supported in part by a grant by the Sloan Foundation to the Center for Systems Neuroscience, University of Massachusetts

Rights and permissions

Reprints and permissions

About this article

Cite this article

Amari, SI. Neural theory of association and concept-formation. Biol. Cybernetics 26, 175–185 (1977). https://doi.org/10.1007/BF00365229

Download citation

  • Received:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF00365229

Keywords

Search

Navigation