Discrete-Time Neuro Identification Without Robust Modification
IEE PROCEEDINGS-CONTROL THEORY AND APPLICATIONS(2003)
摘要
In general, neural networks cannot exactly represent nonlinear systems. A neuro identifier has to include robust modification in order to guarantee Lyapunov stability. An input-to-state stability approach is used to create robust training algorithms for discrete-time neural networks. It is concluded that the gradient descent law and a backpropagation-type algorithm used for the weight adjustments are stable in the sense of L-infinity and robust to any bounded uncertainties.
更多查看译文
关键词
discrete time,stability,backpropagation,identification,neural networks,nonlinear system,neural nets,nonlinear systems
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要