State estimation for proportional delayed complex-valued memristive neural networks
Yongkang Zhang, Liqun Zhou
Abstract
The paper addresses the issue of state estimation for a kind of complex-valued memristive neural networks (CVMNNs) accompanied by proportional delays, without applying regular split method of CVMNNs. By virtue of constructing pertinent Lyapunov functional (LF), and deploying matrix inequality techniques, various delay-dependent principles for scrutinizing the asymptotical stability of the estimation error system of the CVMNNs are constituted by linear matrix inequalities (LMIs) with CV variables. Examples are portrayed to manifest the validity and accuracy of the raised principles, and demonstrated applications in image security.
Topics & Concepts
Artificial neural networkState (computer science)EstimationComputer scienceControl theory (sociology)Artificial intelligenceMathematicsAlgorithmControl (management)EngineeringSystems engineeringAdvanced Memory and Neural Computingstochastic dynamics and bifurcationNeural Networks Stability and Synchronization