Stability analysis of inertial neural networks: A case of almost anti‐periodic environment

Abstract

In this paper, a class of inertial neural networks with time delays is considered. By developing an approach based on differential inequality techniques coupled with Lyapunov function method, some assertions are demonstrated to guarantee the exponential stability of almost anti‐periodic solutions for the dynamical system described the model. Finally, two numerical examples to illustrate the feasibility of our theoretical outcomes.

A novel adaptive control design for exponential stabilization of memristor‐based CVNNs with time‐varying delays using matrix measures

“…Complex‐valued recurrent neural networks (CVNNs) are constructed by substituting real‐valued components with their complex‐valued counterparts, such as state vectors, connection weights, activation functions, external inputs, and outputs. This approach mirrors the advancement and expansion of neural networks (NNs) in the real domain 1–5 . The CVNNs have garnered significant attention due to their extensive utilization in several domains, such as filtering, computer vision, remote sensing, quantum devices 6,7 .…”

Robust stability of uncertain stochastic switched inertial neural networks with time‐varying delay using state‐dependent switching law

“…Remark The stability results of some types of INNs were given in [33–35, 39] and [44] without using state‐dependent switching method. However, the stability results of SSINNs () and SSINNs () are considered in this paper using state‐dependent switching method, therefore, our results are significant over the results obtained in the previous works [33–35, 39, 44] and the stability results of SSNNs without inertial term are presented in [49, 57] and [58].…”

“…Remark The stability results of some types of INNs were given in [33–35, 39] and [44] without using state‐dependent switching method. However, the stability results of SSINNs () and SSINNs () are considered in this paper using state‐dependent switching method, therefore, our results are significant over the results obtained in the previous works [33–35, 39, 44] and the stability results of SSNNs without inertial term are presented in [49, 57] and [58]. In [57] and [58], authors studied the stability of stochastic switched NNs with parameter uncertainties with random disturbances alone or the stability analysis of stochastic switched NNs with time‐varying delay alone.…”

“…The term "inertial" is viewed as a critical tool and is used to describe complicated bifurcation behavior and chaos. Thus, INNs have more practical applications in areas like autonomous control, predictive estimation, and signal processing and have attracted wide attention; for details, see [32][33][34][35][36][37][38][39][40][41][42][43][44]. In particular, finite-time stabilization for switched inertial neural networks (SINNs) with time delay is investigated in [32] using a variable transformation method and LKF with a delayed or non-delayed nonlinear feedback controller.…”

Time-Varying Heterogeneous Alternation Control for Synchronization of Delayed Neural Networks

“…S YNCHRONIZATION has garnered substantial attention in theoretical analysis [1]- [5] and technical application [6], [7] as a key aspect of understanding neural network [8]. Actually, extra control is usually required to achieve this task for many systems due to the complexities between nodes and the node dynamics.…”