Global Asymptotic Stability of Anti-Periodic Solutions of Time-Delayed Fractional Bam Neural Networks

Abstract

AbstractIn this study, bidirectional fractional-order BAM neural networks with time-varying delays are examined. Time delay is an important phenomenon in the implementation of a signal or effect passing through neural network. Signal transmission in neural networks can generally be described as an anti-periodic process. Our aim is to show global asymptotic stability and the uniqueness of the equilibrium point for such neural networks in the problem with antiperiodic solution.For this purpose, the proof was made using differential inequality theory, basic analysis information, and the Lyapunov functional method. In addition, a numerical example is presented to verify the theoretical results.