State estimation of neural networks with both time-varying delays and norm-bounded parameter uncertainties via a delay decomposition approach

• The time-varying delay interval is divided into multiple time-varying segments.
• Convex combination expresses the upper bound of the derivative of the LK functional.
• Both the Lyapunov stability theory and free-weighting matrix approach are used.

This paper is concerned with the state estimation problem for neural networks with both time-varying delays and norm-bounded parameter uncertainties. By employing a delay decomposition approach and a convex combination technique, we obtain less conservative delay-dependent stability criteria to guarantee the existence of desired state estimator for the delayed neural networks. Finally, numerical examples are presented to demonstrate the effectiveness of the proposed approach.