Exponential \({H_\infty }\) Filtering for Discrete-Time Switched Neural Networks with Mode-Dependent Average Dwell Time
摘要
This paper studies the exponential \(H_\infty \) filtering problem for discrete-time switched neural networks (SNNs) under mode-dependent average dwell time (MDADT). First, we establish the global uniform exponential stability for the filtering error system. Second, we quantify noise attenuation through a weighted \(l_2\) -gain \(H_\infty \) performance index. Finally, numerical simulations demonstrate the validity of derived results.