Abstract
A mathematical model of neural processing is proposed which incorporates a theory for the storage of information. The model consists of a network of neurons that linearly processes incoming neural activity. The network stores the input by modifying the synaptic properties of all of its neurons. The model lends support to a distributive theory of memory using synaptic modification. The dynamics of the processing and storage are represented by a discrete system. Asymptotic analysis is applied to the system to show the learning capabilities of the network under constant input. Results are also given to predict the network's ability to learn periodic input, and input subjected to small random fluctuations.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Deutsch, J. A.: The cholinergic synapse and the site of memory. Science174, 788–794 (1971)
Eccles, J. C.: Possible synaptic mechanisms subserving learning. In: Karczmar, A. G., Eccles, J. C. (Eds.): Brain and human behavior, pp. 39–61. Berlin-Heidelberg-New York: Springer 1972
Greenough, W. T.: Experiential modification of the developing brian. Amer. Sci.63, 37–46 (1975)
Horn, G., Rose, S. P. R., Bateson, P. P. G.: Experience and plasticity in the central nervous system. Science181, 506–514 (1973)
Anderson, J. A.: Two models for memory organization using interactive traces. Math. Biosci.8, 137–160 (1970)
Anderson, J. A.: A simple neural network generating an interactive memory. Math. Biosci.14, 197–220 (1972)
Anderson, J. A.: What is a distinctive feature? Techn. Rep. 74-1. Providence: Center for Neural Studies, Brown University 1974
Cooper, L. N.: A possible organization of animal memory and learning. In: Lundquist, B., Lundquist, S. (Eds.): Proceedings of the Nobel symposium on collective properties of physical systems. New York: Academic Press 1973
Grossberg, S.: Non-linear difference-differential equations in prediction and learning theory. Proc. Nat. Acad. Sci. U.S.A.58, 1329–1334 (1967)
Grossberg, S.: Embedding fields. A theory of learning with physiological implications. J. math. Psychol.6, 209–239 (1969)
Lashley, K. S.: In search of the engram. Symp. Soc. exp. Biol.4, 454–482 (1950)
Longuet-Higgins, H. C.: Holographic model of temporal recall. Nature217, 104 (1968)
Willshaw, D. J., Buneman, O. P., Longuet-Higgins, H. C.: Nonholographic associative memory. Nature (Lond.)222, 960–962 (1969)
McGaugh, J. M., Herz, J. J.: Memory consolidation. San Francisco: Albion Publ. Comp. 1972
Mountcastle, V. B.: The problem of sensing and the neural coding of sensory events. In: Quarton, G. C., Melnechuk, T., Schmitt, F. O. (Eds.): The neurosciences: A study program, pp. 393–408. New York: Rockefeller University Press 1967
Pfaff, D.: Parsimonius biological models of memory and reinforcement. Psychol. Rev.76, 70–81 (1969)
Grenander, U., Silverstein, J.: Spectral analysis of networks with random topologies. (submitted to SIAM J. appl. Math.)
Hahn, W.: Stability of motion. Berlin-Heidelberg-New York: Springer 1967
Hurt, J.: Some aspects of difference equations. Ph.D. Thesis. Providence: Brown University, Div. Appl. Math. 1967
Hurt, J.: Some stability theorems for ordinary difference equations, Tech. rep. no. 66-6. Providence: Center for Dynamical Systems, Div. Appl. Math., Brown University 1966
Wilson, H. R., Cowan, J. D.: A mathematical theory of the functional dynamics of cortical and thalamic nervous tissue. Kybernetik13, 55–80 (1973)
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Silverstein, J.W. Asymptotics applied to a neural network. Biol. Cybernetics 22, 73–84 (1976). https://doi.org/10.1007/BF00320132
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF00320132