Paper abstract

[Dr. S. Kak]

The following paper has just been published.

PRAMANA - J. PHYS., Vol. 38, March 1992, pp. 271-278
------------------------------------------------------------------
State Generators and Complex Neural Memories

Subhash C. Kak

Department of Electrical and Computer Engineering Louisiana State
University, Baton Rouge, LA 70803, USA

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 can explain how
stimulating an appropriate neuron can then recall a memory.  Although
the 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.
There are aspects to biological memory that are distributed and
others that are localized.  In the currently popular artificial
neural network models the synaptic weights reflect the stored
memories, which are thus distributed over the network.  The question
then arises whether these models can explain Penfield's observations
on memory localization.  This paper shows that such a localization
does occur in these models if self-indexing is used.  It is also
shown how a generalization of the McCulloch-Pitts model of neurons
appears essential in order to account for certain aspects of
distributed information processing.  One particular generalization,
described in the paper, allows one to deal with some recent findings
of Optican & Richmond (1987).