Convergence analysis of cellular neural networks with unbounded delay

Cellular Neural Networks (CNNs) have been successfully applied in many area s such as classification of patterns, image processing, associative memorie s, etc. Since they are inherently local in nature, they can be easily imple mented in very large scale integration. In the processing of static images, CNNs without delay are often applied whereas in the processing of moving i mages, CNNs with delay have been found more suitable. This paper proposes a more general model of CNNs with unbounded delay, which may have potential applications in processing such motion related phenomena as moving images, and studies global convergence properties of this model. The dynamic behavi ors of CNNs, especially their convergence properties, play important roles in applications. This paper: 1) introduces a class of CNNs with unbounded d elay; 2) gives some interesting properties of a network's output function; 3) establishes relationships between a network's state stability and its ou tput stability; and 4) obtains simple and easily checkable conditions for g lobal convergence by functional differential equation methods.