Robust Learning by Self-organization of Nonlinear Lines of Attractions

  • Ming-Jung Seow
  • Vijayan K. Asari
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3971)


A mathematical model for learning a nonlinear line of attractions is presented in this paper. This model encapsulates attractive fixed points scattered in the state space representing patterns with similar characteristics as an attractive line. The dynamics of this nonlinear line attractor network is designed to operate between stable and unstable states. These criteria can be used to circumvent the plasticity-stability dilemma by using the unstable state as an indicator to create a new line for an unfamiliar pattern. This novel learning strategy utilized stability (convergence) and instability (divergence) criteria of the designed dynamics to induce self-organizing behavior. The self-organizing behavior of the nonlinear line attractor model can helps to create complex dynamics in an unsupervised manner. Experiments performed on CMU face expression database shows that the proposed model can perform pattern association and pattern classification tasks with few iterations and great accuracy.


Face Image Instability Mode Associative Memory Recurrent Network Unsupervised Manner 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Seung, H.S.: Learning Continuous Attractors in Recurrent Networks. Advances in Neural Information Processing Systems, 654–660 (1998)Google Scholar
  2. 2.
    Seow, M.J., Asari, K.V.: Associative Memory Using Nonlinear Line Attractor Network for Multi-Valued Pattern Association. In: Wang, J., Liao, X.-F., Yi, Z. (eds.) ISNN 2005. LNCS, vol. 3496, pp. 485–490. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  3. 3.
    Freeman, W.J., Barrie, J.M.: Analysis of Spatial Patterns of Phase in Neocortical Gamma EEGs in Rabbit. Journal of Neurophysiology 84, 1266–1278 (2000)Google Scholar
  4. 4.
    Harter, D., Kozma, R.: Nonconvergent Dynamics and Cognitive Systems. Cognitive Science (2003)Google Scholar
  5. 5.
    Yao, Y., Freeman, W.J.: Model of Biological Pattern Recognition with Spatially Chaotic Dynamics. Neural Networks 3, 153–170 (1990)CrossRefGoogle Scholar
  6. 6.
    Seow, M.J., Asari, K.V.: Recurrent Network as a Nonlinear Line Attractor for Skin Color Association. In: Yin, F.-L., Wang, J., Guo, C. (eds.) ISNN 2004. LNCS, vol. 3173, pp. 870–875. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  7. 7.
    Perisi, G.: Asymmetric Neural Networks and the Process of Learning. J. Phys. A 19, L675 (1986)CrossRefMathSciNetGoogle Scholar
  8. 8.
    Carpenter, G.A., Grossberg, S.: ART 2: Stable Self-Organization of Pattern Recognition Codes for Analog Input Patterns. Applied Optics 26, 4919–4930 (1987)CrossRefGoogle Scholar
  9. 9.
    Liu, X., Chen, T., Vijaya Kumar, B.V.K.: Face Authentication for Multiple Subjects Using Eigenflow. Pattern Recognition: special issue on Biometric 36, 313–328 (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ming-Jung Seow
    • 1
  • Vijayan K. Asari
    • 1
  1. 1.Department of Electrical and Computer EngineeringOld Dominion UniversityNorfolkUSA

Personalised recommendations