A New Proposal for Implementation of Competitive Neural Networks in Analog Hardware
SBRN '98 Proceedings of the Vth Brazilian Symposium on Neural Networks
Anti-periodic solutions for high-order Hopfield neural networks
Computers & Mathematics with Applications
An anti-periodic solution for a class of recurrent neural networks
Journal of Computational and Applied Mathematics
Stability criteria for set dynamic equations on time scales
Computers & Mathematics with Applications
Colour image segmentation using fuzzy clustering techniques and competitive neural network
Applied Soft Computing
International Journal of Systems Science
Mathematical and Computer Modelling: An International Journal
Global exponential stability of competitive neural networks with different time scales
IEEE Transactions on Neural Networks
Local and Global Stability Analysis of an Unsupervised Competitive Neural Network
IEEE Transactions on Neural Networks
Hi-index | 0.01 |
In this paper, the existence and the global exponential stability of anti-periodic solution for competitive neural networks with delays in the leakage terms are investigated on time scales which unifies the continuous-time and the discrete-time competitive neural networks under the same framework. Firstly, the existence of anti-periodic solution is discussed by using the method of coincidence degree and M-matrices. Then some sufficient conditions are obtained to guarantee the global exponential stability of anti-periodic solution for such neural networks. The obtained results are new and improve some earlier publications. Finally, two examples are given to illustrate the effectiveness of the theoretical results.