Improvement of discrete-time cellular neural networks for associative memory using 2-dimensional discrete Walsh transform

Abstract

The conventional synthesis procedure of discrete-time cellular neural networks (DTCNNs) for associative memory may generate the cells with only self-feedback due to the sparsely interconnected structure. Although this problem is solved by increasing the number of interconnections, hardware implementation becomes very difficult. In this paper we propose the DTCNN system which stores the 2-dimensional discrete Walsh transforms (DWTs) of memory patterns. As each element of DWT involves the information of whole sample data, our system can associate the desired memory patterns which the conventional DTCNN fails to do.