Passivity of memristor-based recurrent neural networks (MRNNs) with multi-proportional delays is investigated in this paper. Here, proportional delay is an unbounded time-varying delay, which is distinct from constant delay, bounded time-varying delay and distributed delay. In the sense of Filippov solution, we present several new sufficient conditions for the passivity of MRNNs with multi-proportional delays, which are delay-independent and delay-dependent, by establishing appropriate Lyapunov functionals and utilizing inequality techniques. The passivity criteria here are presented in the form of linear matrix inequalities (LMIs). Finally, a numerical example and its simulations are given to illustrate the accuracy and validation of the obtained results.
CITATION STYLE
Su, L., & Zhou, L. (2017). Passivity of memristor-based recurrent neural networks with multi-proportional delays. Neurocomputing, 266, 485–493. https://doi.org/10.1016/j.neucom.2017.05.064
Mendeley helps you to discover research relevant for your work.