New Results for Global Exponential Stability of Delayed Cohen-Grossberg Neural Networks.

The exponential stability is discussed for Cohen-Grossberg neural networks with discrete delays. Without assuming the boundedness, differentiability and monotonicity of the activation functions, the nonlinear measure approach is employed to analyze the existence and uniqueness of an equilibrium, and a novel Lyapunov functional is constructed to investigate the exponential stability of the networks. New general sufficient conditions, which are independent of the delays, are derived for the global exponential stability of the delayed neural networks. [ABSTRACT FROM AUTHOR]