期刊文献+

连续BAM神经网络的稳定性分析—LMI/BMI方法 被引量:1

Stability analysis of continuous time BAM neural networks: an LMI/BMI approach
下载PDF
导出
摘要 对于连续双向联想记忆(BAM)神经网络的平衡点的稳定性问题,目前人们已经得到了很多富有意义的成果。本文提出一种新的神经网络模型-标准神经网络模型(SNNM),利用不同的Lyapunov泛函和S方法推导出基于线性/双线性矩阵不等式(LMI/BMI)的SNNM全局渐近稳定性和全局指数稳定性的充分条件。通过状态的线性变换,将连续BAM神经网络转化为SNNM,并利用有关SNNM的稳定性的一些结论,得到连续BAM神经网络平衡点的全局渐近稳定性和全局指数稳定性的充分条件,这些条件都以LMI或BMI形式给出,容易验证,保守性低。该方法扩展了以前的稳定性结果,同时也适用于其它类型的递归神经网络的稳定性分析。 So far many fruitful results have been obtained for stability of equilibrium points of continuous time bidirectional associative memory (BAM) neural network. A novel neural network model termed standard neural network model (SNNM) was advanced. By combining a number of different Lyapunov functional with S-procedure, some useful linear/bilinear matrix inequality (LMI/BMI)-based criteria for the global asymptotic stability and global exponential stability of the SNNM were derived. By using state affine transformation, the BAM neural networks were converted to the SNNMs. Based on some results of the SNNMs’ stability, some sufficient conditions for the global asymptotic stability and global exponential stability of the continuous time BAM neural networks were obtained, which were formulated as easily verifiable LMIs or BMIs, whose conservativeness is relatively low. The proposed approach improves the known stability results, and can also be applied to other forms of recurrent neural networks.
作者 刘妹琴
出处 《电路与系统学报》 CSCD 北大核心 2005年第3期52-57,共6页 Journal of Circuits and Systems
基金 国家自然科学基金资助项目(60374028)
关键词 标准神经网络模型(SNNM) 双向联想记忆(BAM) 线性/双线性矩阵不等式(LMI/BMI) 渐近稳定 指数稳定性 standard neural network model (SNNM) bidirectional associative memory (BAM) linear/bilinear matrix inequality (LMI/BMI) asymptotic stability exponential stability
  • 相关文献

参考文献13

  • 1Kosko B. Adaptive bidirectional associative memories[J]. Appl. Opt., 1987, 26(23): 4947-4960.
  • 2傅予力,赵勇,范衠,廖晓昕.时滞离散时间双向联想记忆模型的研究[J].华中理工大学学报,2000,28(7):80-82. 被引量:2
  • 3Cao J D, Wang L. Exponential stability and periodic oscillatory solution in BAM networks with delays[J]. IEEE Trans. on Neural Networks, 2002, 13(2): 457-463.
  • 4Zhang B L, Xu B Z, Kwong P K. Performance analysis of the bidirectional associative memory and an improved model from the matched-filtering viewpoint[J]. IEEE Trans. on Neural Networks, 1993, 4(5): 864-872.
  • 5Xu B Z, Zhang B L, Kwong C P. Asymptotic stability analysis of continuous bidirectional associative memory networks[A]. IEEE International Conference on Systems Engineering[C]. Kobe, Japan, 1992. 572-575.
  • 6金聪.连续双向联想记忆网络的渐近稳定性[J].模式识别与人工智能,1997,10(1):81-86. 被引量:3
  • 7Moore J B, Anderson B D O. A generalization of the Popov criterion[J]. Journal of the Franklin Institute, 1968, 285(6): 488-492.
  • 8Boyd S P, Ghaoui L E, Feron E, Balakrishnan V. Linear matrix inequalities in system and control theory[M]. Philadelphia, PA: SIAM, 1994.
  • 9Suykens J A K, Vandewalle J, Moor B D. An absolute stability criterion for the Lur'e problem with sector and slope restricted nonlinearities[J]. IEEE Trans. on Circuits and Systems-I, 1998, 45(9): 1007-1009.
  • 10Liao X F, Chen G R, Sanchez E N. Delayed-dependent exponential stability analysis of delayed neural networks: an LMI approach[J]. Neural Networks, 2002, 15(7): 855-866.

二级参考文献13

  • 1游兆永,李磊.共轭广义对角占优矩阵的特征值分布[J].Journal of Mathematical Research and Exposition,1989,9(2):309-310. 被引量:26
  • 2孙玉祥,数学杂志,1987年,7卷,2期,143页
  • 3逢明贤,数学年刊.A,1985年,6卷,3期,323页
  • 4Rao S V H,Neural Netowrks,1999年,12卷,2期,455页
  • 5Zhang Shunian,Computers Math Appli,1997年,33卷,1期,41页
  • 6Wang Zhengou,IEEE Trans Computers,1996年,45卷,10期,1171页
  • 7Yen G G,IEEE Trans Neural Networks,1995年,6卷,8期,1293页
  • 8Boyd S,Ghaoui LE,Feron E,et al.Linear Matrix Inequalities in System and Control Theory,1994.
  • 9Suykens J A K;VANDEWALLE J P L;DE MOOR B L R.Artificial neural networks for modeling and control of non-linear systems,1996.
  • 10Tanaka K.An approach to stability criteria of neural network control systems[J],1996(03).

共引文献7

同被引文献19

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