Boundedness and global convergence of non-autonomous neural networks with variable delays

This paper is concerned with the boundedness and global convergence of the solutions of a non-autonomous system with variable delays, arising from the description of the states of neurons in delayed Hopfield neural networks in a time-varying situation. By using the analysis method, inequality technique and the properties of MM-matrix, several novel sufficient conditions ensuring the boundedness and global convergence of all solutions are established. Our results are new and complement previously known results. The theoretical analysis is verified by numerical simulations.