Peak-to-peak exponential direct learning of continuous-time recurrent neural network models: a matrix inequality approach

Journal of inequalities and applications

Choon Ki Ahn¹ 

关键词: exponential peak-to-peak norm performance;    training law;    dynamic neural network models;    disturbance;    matrix inequality;   

DOI  :  10.1186/1029-242X-2013-68

学科分类：数学（综合）

来源: SpringerOpen

【 摘 要 】

The purpose of this paper is to propose a new peak-to-peak exponential direct learning law (P2PEDLL) for continuous-time dynamic neural network models with disturbance. Dynamic neural network models trained by the proposed P2PEDLL based on matrix inequality formulation are exponentially stable, with a guaranteed exponential peak-to-peak norm performance. The proposed P2PEDLL can be determined by solving two matrix inequalities with a fixed parameter, which can be efficiently checked using existing standard numerical algorithms. We use a numerical example to demonstrate the validity of the proposed direct learning law.

【 授权许可】

CC BY