Advertisement

Stability Analysis of Discrete Hopfield Neural Networks with Weight Function Matrix

  • Jun Li
  • Yongfeng Diao
  • Jiali Mao
  • Ying Zhang
  • Xing Yin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5370)

Abstract

Most matrixes of Discrete Hopfield neural networks(DHNNs) and DHNNs with delay are constant matrixes. However, most weight matrixes of DHNNses are variable in many realistic systems. So, the weight matrix and the threshold vector with time factor are considered, and DHNNs with weight function matrix (DHNNWFM) is described. Moreover, the result that if weight function matrix and threshold function vector respectively converge to a constant matrix and a constant vector that the corresponding DHNNs is stable or the weight matrix function is a symmetric function matrix, then DHNNWFM is stable, is obtained by matrix analysis.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Hopfield, J.J.: Neural networks and physical systems emergent collective computational abilities. Proc. Nat. Acad. Sci. USA 79, 2554–2558 (1982)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Bruck, J., Goodman, J.W.: A generalized convergence theorem for neural networks. IEEE Trans. on Inform Theory 34, 1089–1092 (1988)MathSciNetCrossRefzbMATHGoogle Scholar
  3. 3.
    Goles, E., Fogelman, F., Pellegrin, D.: Decreasing energy functions as a tool for studying threshold Network. Discrete Applied Mathematics 12, 261–277 (1985)MathSciNetCrossRefzbMATHGoogle Scholar
  4. 4.
    Xu, Z.B., Kwong, C.P.: Global Convergence and Asymptotic Stability of Asymmetric Hopfield Neural Networks. J. Mathematical Analysis and Applications 191, 405–427 (1995)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Lee, D.L.: New stability conditions for Hopfield neural networks in partial simultaneous update mode. IEEE Trans. on Neural Networks 10, 975–978 (1999)CrossRefGoogle Scholar
  6. 6.
    Xiang, H., Yan, K.M., Wang, B.Y.: Existence and global exponential stability of periodic solution for delayed high-order Hopfield-type neural networks. Physics Letters A 352, 341–349 (2006)CrossRefzbMATHGoogle Scholar
  7. 7.
    Zhang, Q., Wei, X., Xu, J.: On Global Exponential Stability of Discrete-Time Hopfield Neural Networks with Variable Delays. Discrete Dynamics in Nature and Society. Article ID: 67675, 9p (2007)Google Scholar
  8. 8.
    Xu, B., Liu, X., Liao, X.: Global asymptotic stability of high-order Hopfield type neural networks with time delays. Comput. Math. Appl. 45(10-11), 1729–1737 (2003)MathSciNetCrossRefzbMATHGoogle Scholar
  9. 9.
    Kosmatopoulos, E.B., Polycarpou, M.M., Christodoulou, M.A., Ioannou, P.A.: High-order neural network structures for identification of dynamical systems. IEEE Trans. Neural Networks 6(2), 422–431 (1995)CrossRefGoogle Scholar
  10. 10.
    Xiang, H., Yan, K.M., Wang, B.Y.: Existence and global exponential stability of periodic solution for delayed discrete high-order Hopfield-type neural networks. Discrete Dynamics in Nature and Society 3, 281–297 (2005)CrossRefzbMATHGoogle Scholar
  11. 11.
    Bellman, R.: Introduction to Matrix analysis. The Rand Corporation (1970)Google Scholar
  12. 12.
    Stoer, J., Bulirsch, R.: Introduction to Numerical analysis. Springer, New York (1980)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Jun Li
    • 1
  • Yongfeng Diao
    • 1
  • Jiali Mao
    • 1
  • Ying Zhang
    • 1
  • Xing Yin
    • 2
  1. 1.School of Computer ScienceChina West Normal UniversityNanchongChina
  2. 2.School of Computer SciencePan Zhi Hua UniversityPanzhihuaChina

Personalised recommendations