Improved exponential stability criteria for time-varying delayed neural networks

This paper is concerned with the exponential stability for neural networks with mixed time-varying delays. By using a more general delay-partitioning approach, an augmented Lyapunov functional that contains some information about neuron activation function is constructed. In order to derive less conservative results, an adjustable parameter is introduced to divide the range of the activation function into two unequal subintervals. Moreover, the application of combination of integral inequalities further reduces the conservativeness of the obtained exponential stability conditions. Numerical examples illustrate the advantages of the proposed conditions when compared with other results from the literatures.