Simplified exponential stability analysis for recurrent neural networks with discrete and distributed time-varying delays

This paper provides simplified exponential stability criteria for a class of recurrent neural networks (RNNs) with discrete and distributed time-varying delays. The activation functions of the RNNs are assumed to be more general, and the proposed criteria are obtained by only using a integral inequality and are not involved any free-weighting matrices. This feature makes the computational burden largely reduced. Numerical examples are given to demonstrate the effectiveness and the benefits of the proposed method.