|
ABSOLUTE EXPONENTIAL STABILITY OF A CLASS OF NEURAL NETWORKS
Changyin Sun**, Shumin Fei**, Kanjian Zhang**, Jinde Cao*** and Chun-Bo Feng**
** Research Institute of Automation, Southeast University, Nanjing 210096, P. R. China
Email: infcon@seu.edu.cn
*** Department of Mathematics, Southeast University, Nanjing 210096, P. R. China
Email: jdcao@seu.edu.cn
This paper investigates the absolute exponential stability (AEST) of a class of neural networks with a general class of partially Lipschitz continuous and monotone increasing activation functions. The main obtained result is that if the interconnection matrix T of the neural system satisfies that -T is an H-matrix with nonnegative diagonal elements, then the neural system is AEST.
Keywords: Abslute expontential stability, activaton functions, partial Lipschtz continuty, neural networks
Session slot T-Fr-A21: Posters of Learning, Stochastic, Fuzzy and Nerural Systems/Area code 3e : Fuzzy and Neural Systems
 | 