Absolute Exponential Stability Analysis of Recurrent Neural Networks with Generalized Activation Function:An LMI Approach

摘要：

This paper is devoted to study the absolute ex-ponential stability of recurrent neural network with novelgeneralized activation function,which is recently proposed inmy previous paper.By integrating Lyapunov stability theoryand LMI approach,the stability criterion is derived,which isin form of LM! with slack variables.It may enlarge the range inselecting neural networksparameters.Moreover,the stabilitycriteria become less conservative than my previous paper.

关键词： Recurrent neural networks Absolute exponen-tial stability Linear Matrix Inequality.

作者: Jun Xu

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 842-847

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）