Title :
Bifurcation of a class of discrete-time neural networks
Author :
Zhou, Xiaoliang ; Gao, Xueliang
Author_Institution :
Dept. of Math., Guangdong Ocean Univ., Zhanjiang
Abstract :
In this paper, a class of discrete-time system modeling a network with two neurons is considered. Its flip bifurcations (also called period-doubling bifurcations for map) are demonstrated by deriving the equation describing the flow on the center manifold. In particular, the explicit formula for determining the direction and the stability of flip bifurcations are obtained. The theoretical analysis is verified by numerical simulations.
Keywords :
bifurcation; discrete time systems; neural nets; discrete-time neural networks; discrete-time system modeling; flip bifurcations; period-doubling bifurcations; Bifurcation; Electronic mail; Hopfield neural networks; Mathematics; Neural networks; Neurons; Oceans; Stability; Sufficient conditions; Transfer functions;
Conference_Titel :
Cybernetics and Intelligent Systems, 2008 IEEE Conference on
Conference_Location :
Chengdu
Print_ISBN :
978-1-4244-1673-8
Electronic_ISBN :
978-1-4244-1674-5
DOI :
10.1109/ICCIS.2008.4670740
