论文部分内容阅读
This paper proposes an L2 -L∞ learning law as a new learning method for dynamic neural networks with external disturbance. Based on linear matrix inequality (LMI) formulation, the L2-L∞ learning law is presented to not only guarantee asymptotical stability of dynamic neural networks but also reduce the effect of external disturbance to an L2-L∞ induced norm constraint. It is shown that the design of the L2-L∞ learning law for such neural networks can be achieved by solving LMIs, which can be easily facilitated by using some standard numerical packages. A numerical example is presented to demonstrate the validity of the proposed learning law.
Based on linear matrix inequality (LMI) formulation, the L2-L∞ learning law is presented to not only only guarantee asymptotical stability of dynamic neural networks but also reduce the effect of external disturbance to an L2-L∞ induced norm constraint. It is shown that the design of the L2-L∞ learning law for such neural networks can be achieved by solving LMIs, which can be easily facilitated by using some standard numerical packages. A numerical example is presented to demonstrate the validity of the proposed learning law.