In this paper we introduce a class of third-order Cellular Neural Networks (CNN's) with competitive (inhibitory) interconnections between distinct neurons. We highlight the crucial importance of the neuron interconnection symmetry to ensure convergence of trajectories towards equilibrium points (complete stability). Indeed, the main contribution is that there are nonsymmetric competitive CNN's of this class whose interconnection matrix may be chosen arbitrarily close to a symmetric matrix, for which almost all trajectories persistently oscillate.

DI MARCO, M., Forti, M., Tesi, A. (1999). Oscillations in a class of third-order cellular neural networks. In 38-th Conference on Decision and Control (pp.695-700) [10.1109/CDC.1999.832869].

Oscillations in a class of third-order cellular neural networks

DI MARCO, MAURO;FORTI, MAURO;
1999-01-01

Abstract

In this paper we introduce a class of third-order Cellular Neural Networks (CNN's) with competitive (inhibitory) interconnections between distinct neurons. We highlight the crucial importance of the neuron interconnection symmetry to ensure convergence of trajectories towards equilibrium points (complete stability). Indeed, the main contribution is that there are nonsymmetric competitive CNN's of this class whose interconnection matrix may be chosen arbitrarily close to a symmetric matrix, for which almost all trajectories persistently oscillate.
1999
0780352505
DI MARCO, M., Forti, M., Tesi, A. (1999). Oscillations in a class of third-order cellular neural networks. In 38-th Conference on Decision and Control (pp.695-700) [10.1109/CDC.1999.832869].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11365/25811