1 Introduction
Neural networks have been widely used in many technical fields and have achieved great success [1], [2]. Due to hardware limitations or other factors, time delays are inevitably caused during the implementation of neural networks [3]. It is known that the existence of those time-varying delays generally has a negative impact on the performance of neural networks, especially the stability [4]. Most applications of artificial neural networks depend on their stability. For this reason, the issue about analyzing the stability of delayed neural networks (DNNs) is a hot topic, and has received considerable attention [5], [6].