On global asymptotic stability of recurrent neural networks with time-varying delays
Applied Mathematics and Computation
Passive learning and input-to-state stability of switched Hopfield neural networks with time-delay
Information Sciences: an International Journal
IEEE Transactions on Neural Networks
Communications of the ACM
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
Information Sciences: an International Journal
| Hi-index | 0.01 |
This paper investigates the exponential stability problem about the memristor-based recurrent neural networks. Having more rich dynamic behaviors, neural networks based on the memristor will play a key role in the optimistic computation and associative memory, therefore, stability analysis of memristor-based neural networks are quite important. Based on the knowledge of memristor and recurrent neural network, the model of the memristor-based recurrent neural networks is established; and the stability of memristor-based neural networks with time-varying delays is studied. Several sufficient conditions for the global exponential stability of these neural networks are presented. These results ensure global exponential stability of memristor-based neural networks in the sense of Filippov solutions. In addition to providing criteria for memristor-based neural networks with time-varying delays, these stability conditions can also be used for memristor-based neural networks with constant time delays or without time delays. Furthermore, it is convenient to estimate the exponential convergence rates of this neural network by using the results. An illustrative example is given to show the effectiveness of the obtained results.