Further results on passivity analysis of neural networks with time-varying delay

This paper deals with the problem of passivity analysis for neural networks with both time-varying delay and norm-bounded parameter uncertainties. By further utilizing the information of activation function and employing a reciprocally convex approach to consider the relationship between the time-varying delay and its time-varying interval, some improved delay-dependent passivity conditions are obtained, which are formulated in terms of linear matrix inequalities (LMIs) and can be readily solved by existing convex optimization algorithms. Finally, a numerical example is provided to verify the effectiveness of the proposed techniques.