期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

Global Exponential Periodicity of a Class of Recurrent Neural Networks with Non-Monotone Activation Functions and Time-Varying Delays

Global Exponential Periodicity of a Class of Recurrent Neural Networks with Non-Monotone Activation Functions and Time-Varying Delays
原文传递
导出
摘要 The stability of a periodic oscillation and the global exponential class of recurrent neural networks with non-monotone activation functions and time-varying delays are analyzed. For two sets of activation functions, some algebraic criteria for ascertaining global exponential periodicity and global exponential stability of the class of recurrent neural networks are derived by using the comparison principle and the theory of monotone operator. These conditions are easy to check in terms of system parameters. In addition, we provide a new and efficacious method for the qualitative analysis of various neural networks. The stability of a periodic oscillation and the global exponential class of recurrent neural networks with non-monotone activation functions and time-varying delays are analyzed. For two sets of activation functions, some algebraic criteria for ascertaining global exponential periodicity and global exponential stability of the class of recurrent neural networks are derived by using the comparison principle and the theory of monotone operator. These conditions are easy to check in terms of system parameters. In addition, we provide a new and efficacious method for the qualitative analysis of various neural networks.
作者 LI Biwen
机构地区 School of Mathematics and Statistics
出处 《Wuhan University Journal of Natural Sciences》 CAS 2009年第6期475-480,共6页 武汉大学学报（自然科学英文版）
基金 Supported by the Natural Science Foundation of Hubei Province (2007ABA124) the Youth Project Foundation of Hubei Province Education Department (Q200722001) the Major Foundation of Hubei Province Education Department (D200722002)
关键词 recurrent neural networks non-monotone activation functions global exponential stability comparison principle monotone operator recurrent neural networks non-monotone activation functions global exponential stability comparison principle monotone operator
分类号 TP18 [自动化与计算机技术—控制理论与控制工程] TP183 [自动化与计算机技术—控制理论与控制工程]
  • 相关文献

参考文献10

  • 1Townley S,,Hchmann A,Weiss M G, et al.Existence and Learning of Oscillations in Recurrent Neural Networks[].IEEE Transactions on Neural Networks.2000
  • 2Cao J,Wang L.Exponential Stability and Periodic Oscillatory Solution in BAM Networks with Delays[].IEEE Trans Neu- ral Networks.2000
  • 3Guo S,Huang L,Dai B, et al.Golbal Existence of Periodic Solutions of BAM Neural Networks with Variable Coeffi- cients[].Physics Letters.2003
  • 4Chen B,Wang J.Golbal Exponential Periodicity and Global Exponential Stability of a Class of Eecurrent Neural Net- works[].Physics Letters.2004
  • 5Hale JK.Theory of functional differential equations[]..1977
  • 6Nishikawa,T,Lai,YC,Hoppensteadt,FC.Capacity of oscillatory associative-memory networks with error-free retrieval[].Physical Review Letters.2004
  • 7K. Chen,D.L. Wang and X.W. Liu.Weight adaptation and Oscillatory Correlation for Image Segmentation[].IEEE Transactions on Neural Networks.2000
  • 8Ruiz,A,Owens,D,Townley,S.Existence, learning, and replication of periodic motions in recurrent neural networks[].IEEE Transactions on Neural Networks.1998
  • 9JIN H L,Zacksenhouse M.Oscillatory neural net-works for robotic yoyo control[].IEEE Transactions on Neural Networks.2003
  • 10Meifang Dong.Global exponential stability and existence of periodic solutions of CNNs with delays[].Physics Letters.2002
Wuhan University Journal of Natural Sciences
2009年 第6期

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