Global Exponential Stability of Reaction-Diffusion Neural Networks with Both Variable Time Delays and Unbounded Delay
In the paper, the reaction-diffusion neural network models with both variable time delays and unbounded delay are investigated. These models contain weaker activation functions than partially or globally Lipschitz continuous functions. Without assuming the boundedness, monotonicity and differentiability of the active functions, algebraic criteria ensuring existence, uniqueness and global exponential stability of the equilibrium point are obtained.
KeywordsNeural Network Equilibrium Point Cellular Neural Network Lipschitz Continuous Function Hopfield Neural Network
Unable to display preview. Download preview PDF.
- 6.Liao, X., Fu, Y.: Stability of Hopfield Neural Networks with Reaction-Diffusion Terms. Acta Electronica Sinica 1, 78–80 (2000)Google Scholar
- 7.Wang, L., Xu, D.: Global Stability of Reaction-Diffusion Hopfield Neural Networks with Variable Time Delay. Science in China (serial E) 6, 488–495 (2003)Google Scholar