Abstract: In this paper, the global exponential stability of anti-periodic solutions of a class of cellular neural networks with proportional delays is discussed. Firstly, a class of cellular neural networks with proportional delays is transformed equivalently into a class of cellular neural networks with constant delays and variable coefficients by a nonlinear transformation. Then, by establishing appropriate delay differential inequalities and applying inequality technique, a delay-dependent sufficient condition is obtained to ensure the existence and global exponential stability of anti-periodic solutions of the system. Finally, the numerical results indicate the proposed method is correct and less conservative than the existing results.

Key words: proportional delays, cellular neural networks, anti-periodic solution, exponential stability