VLSI implementation of cellular neural networks

Abstract

A cellular neural network (CNN) which is an example of very-large-scale analog processing or collective analog computation is presented. The CNN architecture combines some features of fully connected analog neural networks with the nearest-neighbor interactions found in cellular automata. VLSI implementation of these circuits is discussed. Though the circuits described have been fabricated for noise removal and connected segment extraction, most of the features of the VLSI circuits are shared by VLSI implementations of other processing functions.< >