期刊文献+

Global stability of interval recurrent neural networks 被引量:1

Global stability of interval recurrent neural networks
下载PDF
导出
摘要 The robust global exponential stability of a class of interval recurrent neural networks(RNNs) is studied,and a new robust stability criterion is obtained in the form of linear matrix inequality.The problem of robust stability of interval RNNs is transformed into a problem of solving a class of linear matrix inequalities.Thus,the robust stability of interval RNNs can be analyzed by directly using the linear matrix inequalities(LMI) toolbox of MATLAB.Numerical example is given to show the effectiveness of the obtained results. The robust global exponential stability of a class of interval recurrent neural networks(RNNs) is studied,and a new robust stability criterion is obtained in the form of linear matrix inequality.The problem of robust stability of interval RNNs is transformed into a problem of solving a class of linear matrix inequalities.Thus,the robust stability of interval RNNs can be analyzed by directly using the linear matrix inequalities(LMI) toolbox of MATLAB.Numerical example is given to show the effectiveness of the obtained results.
出处 《Journal of Beijing Institute of Technology》 EI CAS 2012年第3期382-386,共5页 北京理工大学学报(英文版)
基金 Supported by the Natural Science Foundation of Shandong Province (ZR2010FM038,ZR2010FL017)
关键词 recurrent neural networks(RNNs) interval systems linear matrix inequalities(LMI) global exponential stability recurrent neural networks(RNNs) interval systems linear matrix inequalities(LMI) global exponential stability
  • 相关文献

参考文献18

  • 1Meng Joo Er, Wu Shiqian,Lu Juwei,et al. Facerecognition with radial basis function ( RBF) neuralnetworks [ J]. IEEE Trans Neural Networks, 2002,13(3) : 697 -710.
  • 2Meng Joo Er, Gao Yang. Robust adaptive control ofrobot manipulators using generalized fuzzy neuralnetworks [ J]. IEEE Trans on Industrial Electron-ics, 2003,50(3) : 620 -628.
  • 3Forti M,Manetti S,Marini M. Necessary and suffi-cient condition for absolute stability of neural net-works [J]. IEEE Trans Circuits and Systems I,1994,41(7) : 491 -494.
  • 4Yi Zhang, Tan Kok-Kiong. Multistability of discrete-time recurrent neural networks with unsaturatingpiecewise linear activation functions [ J ]. IEEETrans Neural Networks, 2004,15(2) : 329 -336.
  • 5Zhang Qiang, Ma Runnian, Xu Jin. Stability of cel-lular neural networks with delay [ J ]. ElectronicsLetters, 2001,37(9) : 575 -576.
  • 6Huang Y S, Wu Chai-Wah. A unifying proof of glob-al asymptotical stability of neural networks with de-lay [J]. IEEE Trans Circuits and Systems II,2005,52(4) : 181 -184.
  • 7Cao Jinde,Wang Jun. Absolute exponential stabilityof recurrent neural networks with Lipschitz-continu-ous activation functions and time delays [ J]. Neu-ral Networks, 2004,17(3) : 379 -390.
  • 8Liao Xiaofeng, Yu Juebang, Chen Guanrong. Novelstability criteria for bidirectional associative memoryneural networks with time delays [ J]. Int J CircuitTheory and Applications, 2002,30(5) : 519 -546.
  • 9Xu S,Lam J,Ho D W C, et al. Global robust expo-nential stability analysis for interval recurrent neuralnetworks [ J ]. Physics Letters A,2004,325 (2 ):124 -133.
  • 10Liao Xiaofeng, Wong Kwok-wo. Robust stability ofinterval bidirectional associative memory neuralnetwork with time delays [ J]. IEEE Trans Sys-tems, Man, and Cybernetics, Part B, 2004, 34(2) : 1142 -1154.

同被引文献36

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部