SUPERRESOLUTION ALGORITHMS FOR A MODIFIED HOPFIELD NEURAL NETWORK

The purpose of this paper is to describe the implementation of a superresolution (or spectral extrapolation) procedure on a neural network, based on the Hopfield model. This was first proposed by Abbiss et al. [1]. We show the computational advantages and disadvantages of such an approach for different coding schemes and for networks consisting of very simple two state elements as well as those made up of more complex nodes capable of representing a continuum. With the appropriate hardware, we show that there is a computational advantage in using the Hopfield architecture over some alternative methods for computing the same solution. We also discuss the relationship between a particular mode of operation of the neural network and the regularized Gerchberg-Papoulis algorithm.