A weak condition for global stability of delayed neural networks
MetadataShow full item record
The classical analysis of asymptotical and exponential stability of neural networks needs assumptions on the existence of a positive Lyapunov function V and on the strict negativity of the function dV=dt, which often come as a result of boundedness or uniformly almost periodicity of the activation functions. In this paper, we investigate the asymptotical stability problem of Hopfield neural networks with time delays under weaker conditions. By constructing a suitable Lyapunov function, sufficient conditions are derived to guarantee global asymptotical stability and exponential stability of the equilibrium of the system. These conditions do not require the strict negativity of dV=dt, nor do they require that the activation functions to be bounded or uniformly almost periodic.
Showing items related by title, author, creator and subject.
Alchin, Mark David (2011)Australia’s rangelands encompass approximately 80% of the continent and generate significant wealth through a range of industries. The rangelands comprise four major ecosystem types, these are: grasslands, shrublands, ...
Liu, B.; Dam, H.; Teo, Kok Lay; Hill, D. (2017)This article studies KL-stability (the stability expressed by KL-class function) for a class of hybrid dynamical systems (HDS). The notions ofKLK-property andKL-stability are proposed for HDS with respect to the ...
Turner, Sian Elizabeth (2009)Background and research questions. The characterization of chronic persistent asthma in an older adult population is not well defined. This is due to the difficulties in separating the diagnosis of asthma from that of ...