Novel robust exponential stability criteria for neural networks

This paper investigates the problem of robust global exponential stability analysis for uncertain neural networks with interval time-varying delays. The time-delay pattern is quite general and including fast time-varying delays. The values of the time-varying uncertain parameters are assumed to be bounded within given compact sets. The activation functions are monotone nondecreasing with known lower and upper bounds. Novel stability criteria are developed by employing new Lyapunov–Krasovskii functional and the integral inequality. The developed stability criteria are delay dependent and characterized by linear matrix inequalities (LMIs)-based conditions. The developed stability results are less conservative than previous published ones in the literature, which is illustrated by a representative numerical example.