Stability Analysis of a Class of Fractional-order Neural Networks

Abstract

In this paper, the problems of the existence and uniqueness of solutions and stability for a class of fractional-order neural networks are studied by using Banach fixed point principle and analysis technique, respectively. A sufficient condition is given to ensure the existence and uniqueness of solutions and uniform stability of solutions for fractional-order neural networks with variable coefficients and multiple time delays. The obtained results improve and extend some previous works to some extent, and they are easy to check in practice. An illustrative example is presented to show the validity and application of the proposed results.

DOI :http://dx.doi.org/10.11591/telkomnika.v12i2.4409