On the asymptotic behavior of hopfield neural network with periodic inputs
- 27 Downloads
Without assuming the boundedness and differentiability of the nonlinear activation functions, the new sufficient conditions of the existence and the global exponential stability of periodic solutions for Hopfield neural network with periodic inputs are given by using Mawhin's coincidence degree theory and Liapunov's function method.
Key wordsHopfield neural network periodic solution global exponential stability concidence degree Liapunov's function
CLC numbersO175 TN911
Unable to display preview. Download preview PDF.
- LIAO Xiao-xin. Stability of Hopfield networks[J].Science in China Ser A, 1993,23(10): 1025–1035. (in Chinese)Google Scholar
- LIANG Xue-bin, WU Li-de. Global exponential stability of Hopfield networks and applications [J].Science in China Ser A, 1995,25(5): 523–532. (in Chinese)Google Scholar
- LI Tie-cheng, WANG Duo. On the asymptotic behavior of a class artificial neural network with periodic input[J].JCU-Appl Math Ser A, 1997,12(1): 25–28. (in Chinese)Google Scholar
- HUANG Xian-kai. On the existence and stability of periodic solutions for Hopfield neural network equation with delay[J],Applied Mathematics and Mechnics (English Edition), 1999,20(10): 1116–1120.Google Scholar
- Gao J. Periodic oscillation and exponential stability of delayed CNN[J].Physics Letters A, 2000,270(3/4): 157–163.Google Scholar
- Gain R E, Mawhin J L.Coincidence Degree and Nonlinear Differential Equations [M].Lecture Note in Math,567, Berlin: Springer-Verlag, 1977, 40–41.Google Scholar
- Yoshizawa T.Stability Theory by Liapunov's Second Method[M]. Tokyo: The Math Soc of Japan, 1996, 165–169.Google Scholar