The effect of the dimensionality of interconnections on the storage capacity of a threshold controlled neural network

Abstract

The author investigated the effect of the dimensionality of the interconnections in a Hopfield-type network on the storage capacity of the network. The analysis was performed for 1-, 2-, 3- and 4-D interconnection geometries. The capacity was found to be independent of the dimensionality of the interconnections and to depend only on the total number of interconnections available in a given network. In addition, no evidence of any instabilities was observed, in contrast to physical systems of reduced dimensionality.