Global existence and exponential stability of periodic solutions for recurrent neural networks with functional delay

This paper proposes a class of more general model of recurrent neural networks with functional delay, which has been found more suitable to apply directly. Simple and easily checkable conditions of existence, uniqueness, and global exponential stability of periodic solution for the recurrent neural network equations are obtained, utilizing the Lyapunov functional method and the theory of coincidence degree. Some known results are generalized and improved.