On stability of cellular neural networks with delay
P.P. Civalleri, Marco Gilli, Luciano Pandolfi · IEEE Transactions on Circuits and Systems I Fundamental Theory and Applications · 1993
It is known that symmetric cellular neural networks (CNNs) are completely stable. It is shown that CNNs with delay (DCNNs), though symmetric, can become unstable if the delay is suitably chosen: actually such networks can exhibit periodic cycles. Moreover, a sufficient condition is presented to ensure complete stability: such a condition establishes a relation between the delay time and the parameters of the network.>