Global stability of a class of continuous-time recurrent neural networks

Sanqing Hu1, Jun Wang1
1Department of Automation and Computer-Aided Engineering, Chinese University of Hong Kong, Sha Tin, Hong Kong, China

Tóm tắt

This paper investigates global asymptotic stability (GAS) and global exponential stability (GES) of a class of continuous-time recurrent neural networks. First, we introduce a necessary and sufficient condition for the existence and uniqueness of equilibrium of the neural networks with Lipschitz continuous activation functions. Next, we present two sufficient conditions to ascertain the GAS of the neural networks with globally Lipschitz continuous and monotone nondecreasing activation functions. We then give two GES conditions for the neural networks whose activation functions may not be monotone nondecreasing. We also provide a Lyapunov diagonal stability condition, without the nonsingularity requirement for the connection weight matrices, to ascertain the GES of the neural networks with globally Lipschitz continuous and monotone nondecreasing activation functions. This Lyapunov diagonal stability condition generalizes and unifies many of the existing GAS and GES results. Moreover, two higher exponential convergence rates are estimated.

Từ khóa

#Recurrent neural networks #Asymptotic stability #Neural networks #Sufficient conditions #Convergence #Vectors #Quadratic programming #Constraint optimization #Councils #Automation

Tài liệu tham khảo

10.1109/81.404065 10.1109/72.809081 10.1109/10.52325 liang, 1996, necessary and sufficient conditions for absolute exponential stability of hopfield-type neural networks, IEICE TRANS INF &amp SYST, e79 d, 990 10.1109/81.641813 10.1109/81.768832 10.1109/72.883485 10.1016/0893-6080(92)90011-7 roska, 1989, some qualitative aspects of neural computing systems, Proc IEEE ISCAS, 751 10.1109/72.809094 10.1109/31.68298 berman, 1979, Nonnegative Matrices in the Mathematical Sciences michel, 1977, Qualitative Analysis of Large Scale Dynamical Systems 10.1109/72.883412 10.1109/81.298364 vidyasagar, 1993, Nonlinear Systems Analysis 10.1109/81.153645 10.1109/72.839023 10.1109/81.401145 10.1016/0893-6080(88)90021-4 10.1109/81.269055 10.1016/0893-6080(89)90018-X 10.1016/S0893-6080(05)80076-0 10.1137/S0036139997321219 10.1016/0893-6080(93)90014-N 10.1109/72.914530 10.1109/72.914529 10.1002/j.1538-7305.1969.tb01105.x 10.1109/9.917666