Abstract
The mechanism of self-indexing for feedback neural networks that generates memories from short subsequences is generalized so that a single bit together with an appropriate update order suffices for each memory. This mechanism explains how stimulating an appropriate neuron can recall a memory. Although information is distributed in this model, yet our self-indexing mechanism makes it appear localized. Also a new complex valued neuron model is presented to generalize McCulloch-Pitts neurons.
Similar content being viewed by others
References
Amit D, Gutfreund H and Sompolinsky H 1987Phys. Rev. A35 2293
Amit D 1989Modelling the brain (Cambridge: University Press)
Eckhorn R and Popel B 1974Kybernetki 16 191
Hopfield J J 1982Proc. Nat. Acad. Sci. USA 79 2554
Kak S C 1990aPhys. Lett. A143 293
Kak S C 1990b InSym. on the Foundations of Modern Physics, Joensuu, Finland
Lashley K S 1963Brain mechanisms and learning (New York: Dover)
Penfield P and Roberts L 1959Speech and brain mechanisms (Princeton: University Press)
Noest A J 1988Phys. Rev. A38 2196
Optican L M and Richmond B J 1987J. Neurophysiol. 57 162
Prados D and Kak S C 1989 InAdvances in computing and control, (eds) W A Porter, S C Kak and J Aravena (Berlin: Springer-Verlag)
Sperry R 1982Science 217 1223
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Kak, S.C. State generators and complex neural memories. Pramana - J Phys 38, 271–278 (1992). https://doi.org/10.1007/BF02875373
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF02875373