Estimation of attraction domain and exponential convergence rate of dynamic feedback neural nets

This paper obtains some new estimation results about the attraction domain of memory patterns and exponential convergence rate of the network trajectories to memory patterns for continuous associative memory dynamic feedback neural networks. Exponential convergence rate went up faster in our results than those results in the literature. These results can be used for evaluation of fault-tolerance capability and the synthesis procedures for continuous associative memory dynamic feedback neural networks. We give one design example to demonstrate the effectiveness of our theorems.