On Exponential Periodicity And Stability of Nonlinear Neural Networks With Variable Coefficients And Distributed Delays

Abstract

The exponential periodicity and stability of continuous nonlinear neural networks with variable coefficients and distributed delays are investigated via employing Young inequality technique and Lyapunov method. Some new sufficient conditions ensuring existence and uniqueness of periodic solution for a general class of neural systems are obtained. Without assuming the activation functions are to be bounded, differentiable or strictly increasing. Moreover, the symmetry of the connection matrix is not also necessary. Thus, we generalize and improve some previous works, and they are easy to check and apply in practice.