Further Results on Exponentially Robust Stability of Uncertain Connection Weights of Neutral-Type Recurrent Neural Networks

Abstract

Further results on the robustness of the global exponential stability of recurrent neural network with piecewise constant arguments and neutral terms (NPRNN) subject to uncertain connection weights are presented in this paper. Estimating the upper bounds of the two categories of interference factors and establishing a measuring mechanism for uncertain dual connection weights are the core tasks and challenges. Hence, on the one hand, the new sufficient criteria for the upper bounds of neutral terms and piecewise arguments to guarantee the global exponential stability of NPRNN are provided. On the other hand, the allowed enclosed region of dual connection weights is characterized by a four-variable transcendental equation based on the preceding stable NPRNN. In this way, two interference factors and dual uncertain connection weights are mutually restricted in the model of parameter-uncertainty NPRNN, which leads to a dynamic evolution relationship. Finally, the numerical simulation comparisons with stable and unstable cases are provided to verify the effectiveness of the deduced results.

Robustness Analysis of BAM Cellular Neural Network with Deviating Arguments of Generalized Type

“…Robustness is the ability of a control system to maintain a specifc level of performance when certain parameters are perturbed, and it is of great signifcance for the design and application of system. As for the analysis of RoS, there are lots of interesting outcomes, such as, Si et al further studied RoS of dynamical systems with deviating arguments in [26][27][28]; Fang et al analyzed the RoS of fuzzy CNN with deviating argument in [29]. In [30], RoS of recurrent neural network is investigated.…”

Robustness analysis of exponential stability of fuzzy inertial neural networks

“…This is also a motivation for this article. At present, most researches on ROS only focuses on first-order neural networks [26,27,[32][33][34][35][36]. However, in practical applications, due to the inherent special properties of electronic components, high-order neural network models are usually needed to more accurately describe their dynamic behaviors in reality.…”

“…Compared with [14,15], the ROM used in this paper includes two positive variable parameters η i , ξ i , which further expands the ROM used in [14,15] which is only contain one variable parameter. • In addition, in this paper, we have removed the limitation on the derivative of time delay function ς(t) in [33][34][35][36]39], which means that ς ′ (t) ≤ δ < 1 not satisfied in this paper. • The upper limits of time delay and max intensity of noise are obtained respectively by applying Grownwall-Bellman lemma as well as inequality techniques to ensure the perturbed FINNs keep exponential stability.…”