Projective quasi-synchronization of complex-valued recurrent neural networks with proportional delay and mismatched parameters via matrix measure approach

This article is concerned with the projective quasi-synchronization of non-identical complex-valued recurrent neural networks (CVRNNs) with proportional delays and mismatched parameters. The nonlinear Lipschitz activation functions under Lyapunov stability criteria and matrix measure approach have been employed. By designing a suitable controller, a sufficient condition for projective quasi-synchronization criteria of the non-identical CVRNNs model has been derived through the proper description of the matrix measure approach. A significant result for the CVRNNs with mismatched parameters and proportional delays is provided. Finally, a numerical simulation result is given to validate the usefulness and persistence of the theoretical results. The results for different particular cases are displayed graphically.

Automated summary

This article investigates the projective quasi-synchronization problem of non-identical complex-valued recurrent neural networks (CVRNNs) with proportional delays and mismatched parameters. Nonlinear Lipschitz activation functions, Lyapunov stability criteria, and the matrix measure approach are employed. By designing a suitable controller, a sufficient condition for projective quasi-synchronization of the non-identical CVRNNs model is derived using the matrix measure approach. Important results for CVRNNs with mismatched parameters and proportional delays are provided. Numerical simulation results are presented to validate the theoretical results, and graphical representations are shown for different specific cases.