Dissipativity analysis of delayed stochastic generalized neural networks with Markovian jump parameters

Grienggrai Rajchakit, R. Sriraman, R. Samidurai

2021International Journal of Nonlinear Sciences and Numerical Simulation14 citationsDOI

Abstract

Abstract This article discusses the dissipativity analysis of stochastic generalized neural network (NN) models with Markovian jump parameters and time-varying delays. In practical applications, most of the systems are subject to stochastic perturbations. As such, this study takes a class of stochastic NN models into account. To undertake this problem, we first construct an appropriate Lyapunov–Krasovskii functional with more system information. Then, by employing effective integral inequalities, we derive several dissipativity and stability criteria in the form of linear matrix inequalities that can be checked by the MATLAB LMI toolbox. Finally, we also present numerical examples to validate the usefulness of the results.

Topics & Concepts

Artificial neural networkMATLABStability (learning theory)Stochastic neural networkMarkov processApplied mathematicsComputer scienceMathematicsToolboxControl theory (sociology)JumpClass (philosophy)Mathematical optimizationRecurrent neural networkControl (management)Artificial intelligenceMachine learningPhysicsStatisticsProgramming languageOperating systemQuantum mechanicsNeural Networks Stability and SynchronizationMatrix Theory and AlgorithmsStability and Control of Uncertain Systems