Technical communique: New conditions for delay-derivative-dependent stability
Automatica (Journal of IFAC)
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Stability analysis of discrete-time recurrent neural networks with stochastic delay
IEEE Transactions on Neural Networks
A new method for stability analysis of recurrent neural networks with interval time-varying delay
IEEE Transactions on Neural Networks
Novel weighting-delay-based stability criteria for recurrent neural networks with time-varying delay
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
Delay-derivative-dependent stability for delayed neural networks with unbound distributed delay
IEEE Transactions on Neural Networks
Technical communique: Reciprocally convex approach to stability of systems with time-varying delays
Automatica (Journal of IFAC)
Journal of Computational and Applied Mathematics
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A New Criterion of Delay-Dependent Asymptotic Stability for Hopfield Neural Networks With Time Delay
IEEE Transactions on Neural Networks
Improved Delay-Dependent Asymptotic Stability Criteria for Delayed Neural Networks
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
Delay-Slope-Dependent Stability Results of Recurrent Neural Networks
IEEE Transactions on Neural Networks - Part 1
Hi-index | 0.01 |
In this letter, together with some improved Lyapunov-Krasovskii functionals and effective mathematical techniques, several novel sufficient conditions are derived to guarantee a class of delayed neural networks (DNNs) to be asymptotically stable, in which both the time-delay and its time variation can be fully considered. Through combining reciprocal convex technique with earlier convex one, some previously ignored terms can be reconsidered and the stability criteria are presented in terms of LMIs, whose solvability heavily depends on the information on addressed DNNs as much as possible. Finally, it can be demonstrated by two numerical examples that our derived results reduce the conservatism more efficiently than some present ones with some comparing results.