The Dahlquist Constant Approach to Stability Analysis of the Static Neural Networks

摘要

Avoiding the difficulty of constructing a proper Lyapunov function, the generalized Dahlquist constant approach is employed to investigate the exponential stability of the static neural networks. Without assuming the boundedness, monotonicity of the activations, a new sufficient conditions for existence of an unique equilibrium and the exponential stability of the neural networks are presented. An example is given to show the effectiveness of our results.