Chaos and asymptotical stability in discrete-time recurrent neural networks with generalized input-o

• 作 者: 王进良 陈洛南
• 出 处: Science in China,Ser.A
• 发表日期: 2001年02期
• 关键词: Chaos asymptotically chaos bifurcation sufficiently normalized updated eigenvalu

We theoretically investigate the asymptotical stability, local bifurcations and chaos of discrete-time recurrent neural networks with the form ofwhere the input-output function is defined as a generalized sigmoid function, such as vi = tanh(μi,ui), vi =2/πarctan(π/2μiui) and vi =1/(1+e-ui/ε),etc. Numerical simulations are also provided to demonstrate the theoretical results.

We theoretically investigate the asymptotical stability, local bifurcations and chaos of discrete-time recurrent neural networks with the form ofwhere the input-output function is defined as a generalized sigmoid function, such as vi = tanh (μi, ui), vi = 2 / πarctan (π / 2μiui) and vi = 1 / (1 + e-ui / ε), etc. Numerical simulations are also provided to demonstrate the theoretical results.