The Cellular Neural Network Associative Processor, C-NNAP
J. Austin · 1995
. This paper describes a novel associative processor that uses neural associative memories as its processing elements. The machine has been designed to tackle problems in AI and computer vision, using nodes that allow rapid search using inexact information over very large data sets. The associative processor is ideally suited as a pattern processing machine, which is where most of the application work has been centered. This is because it is capable of taking large subsections of images and performing matching and comparisons on these. Each processing element of the associative processor is an Advanced Distributed Associative Memory (ADAM) which is capable of storing large numbers of pattern associations, yet they allow rapid access. As a neural network, the memory performs associative match, not by conventional CAM (Content Addressable Memory) approaches, but by forming a mapping between the patterns to be associated. The benefit of this is rapid access, fault tolerance and an abilit...