Title :
Absolute stability of asymmetric Hopfield neural network
Author :
Gao, Weibing ; Xiong, Yi
Author_Institution :
Seventh Res. Div., Beijing Univ. of Aeronaut. & Astronaut., China
Abstract :
A sufficient absolute stability condition of the asymmetric Hopfield network in terms of the weight matrix is presented. The approach is to reformulate the neural network equation into a nonlinear multivariable feedback system. The authors apply results from nonlinear control system stability theory to derive a sufficient condition to ensure that an asymmetric Hopfield type network equilibrium point is absolutely stable
Keywords :
neural nets; nonlinear control systems; stability; absolute stability; asymmetric Hopfield neural network; network equilibrium point; nonlinear multivariable feedback system; sufficient condition; weight matrix; Biological neural networks; Brain modeling; Capacitance; Hopfield neural networks; Large-scale systems; Neural networks; Neurofeedback; Nonlinear control systems; Nonlinear systems; Stability;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170713
