Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
408995 | Neurocomputing | 2016 | 9 Pages |
This paper presents some novel results on robust finite-time passivity for a class of uncertain discrete-time neural networks (DNNs) with time varying delays. Using the Lyapunov theory together with the zero inequalities, convex combination and reciprocally convex combination approaches, we propose the sufficient conditions for finite-time boundedness and finite-time passivity of DNN for all admissible uncertainties. The results are achieved by using a new Lyapunov-Krasovskii functional (LKF) with novel triple summation terms, several delay-dependent criteria for the DNN are derived in terms of linear matrix inequalities (LMIs) which can be easily verified via the LMI toolbox. Finally, numerical example with simulation scheme have been presented to illustrate the applicability and usefulness of the obtained results.