Autoassociative neural networks for image compression: a massively parallel implementation

Abstract

A massively parallel implementation on the associative string processor (ASP) machine of a neural-network-based technique for image compression is presented. Despite the linear structure of the ASP and the use of fixed arithmetic for the implementation, promising results are shown in terms of learning speed, on the order of 10/sup 9/ connections per second, and the quality of the reconstructed images.<>