Neural Network with Memory and Cognitive Functions

Abstract

This paper provides an analysis of a new class of distributed memories known as R-nets. These networks are similar to Hebbian networks, but are relatively sparsly connected. R-nets use simple binary neurons and trained links between excitatory and inhibitory neurons. They use inhibition to prevent neurons not associated with a recalled pattern from firing. They are shown to implement associative learning and have the ability to store sequential patterns, used in networks with higher cognitive functions. This work explores the statistical properties of such networks in terms of storage capacity as a function of R-net topology and employed learning and recall mechanisms.