Exponential stability of Cohen-Grossberg neural networks
Neural Networks
Existence, learning, and replication of periodic motions in recurrent neural networks
IEEE Transactions on Neural Networks
Existence and learning of oscillations in recurrent neural networks
IEEE Transactions on Neural Networks
Weight adaptation and oscillatory correlation for image segmentation
IEEE Transactions on Neural Networks
Oscillatory neural networks for robotic yo-yo control
IEEE Transactions on Neural Networks
Emergent synchrony in locally coupled neural oscillators
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
In this paper, the periodic oscillation and the global exponential stability of a class of competitive neural networks are analyzed. The competitive neural network considered includes the Hopfield networks, Cohen-Grossberg networks as its special cases. Several sufficient conditions are derived for ascertaining the existence, uniqueness and global exponential stability of the periodic oscillatory state of the competitive neural networks with periodic oscillatory input by using the comparison principle and the theory of mixed monotone operator and mixed monotone flow. As corollary of results on the global exponential stability of periodic oscillation state, we give some results on the global exponential stability of the network modal with constant input, which extend some existing results. In addition, we provide a new and efficacious method for the qualitative analysis of various neural networks.