A partitioning scheme for optoelectronic neural networks

Abstract

Smart pixel technology provides a promising technological alternative for the implementation of the error diffusion network (EDN) because optical input, electronic processing, and optical output are integrated in a single array. While current smart pixel technology could support 256/spl times/256 array sizes, it is of interest to investigate partitioning approaches which use smaller physical array sizes to achieve the same functionality and performance as larger arrays. One approach to this partitioning is to divide a large image into smaller sub-images, multiplex these sub-images into a small smart pixel EDN, and then demultiplex the partitions into the resulting full-sized image. This concept is demonstrated.