New Robust Stability Criterion for Neural Networks of Neutral Type with Time-Varying Delays

Based on Lyapunov stability theory and linear matrix inequality (LMI) technique, robust stability criterion is derived in terms of LMI for a class of neural networks of neutral type with time-varying delays and norm-bounded uncertainties. The result is obtained under mild conditions, assuming neither differentiability nor monotonicity for activation function. And the restriction of the derivative of the discrete time delay is removed. The proposed stability criterion can be checked by the LMI control toolbox in Matlab. Finally, the effectiveness of the result is demonstrated by an example.