Periodic oscillation for a class of neural networks with variable coefﬁcients☆
Nonlinear Analysis: RealWorld Applications 6(2005)545-561，-0001，（）：
In this paper, we study a class of neural networks with variable coefﬁcients which includes delayed Hopﬁeld neural networks, bidirectional associative memory networks and cellular neural networks as its special cases. By matrix theory and inequality analysis, we not only obtain some new sufﬁcient conditions ensuring the existence, uniqueness, global attractivity and global exponential stability of the periodic solution but also estimate the exponentially convergent rate. Our results are less restrictive than previously known criteria and can be applied to neural networks with a broad range of activation functions assuming neither differentiability nor strict monotonicity. Moreover, these conclusions are presented in terms of system parameters and can be easily veriﬁed for the globally Lipschitz and the spectral radius being less than 1. Therefore, our results have an important leading signiﬁcance in the design and applications of periodic oscillatory neural circuits for neural networks with delays. © 2005 Elsevier Ltd. All rights reserved.
版权说明：以下全部内容由郭上江上传于 2010年01月07日 11时19分57秒，版权归本人所有。