Abstract
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.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Seung, H.S.: Learning Continuous Attractors in Recurrent Networks. Advances in Neural Information Processing Systems, 654–660 (1998)
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)
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)
Harter, D., Kozma, R.: Nonconvergent Dynamics and Cognitive Systems. Cognitive Science (2003)
Yao, Y., Freeman, W.J.: Model of Biological Pattern Recognition with Spatially Chaotic Dynamics. Neural Networks 3, 153–170 (1990)
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)
Perisi, G.: Asymmetric Neural Networks and the Process of Learning. J. Phys. A 19, L675 (1986)
Carpenter, G.A., Grossberg, S.: ART 2: Stable Self-Organization of Pattern Recognition Codes for Analog Input Patterns. Applied Optics 26, 4919–4930 (1987)
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)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Seow, MJ., Asari, V.K. (2006). Robust Learning by Self-organization of Nonlinear Lines of Attractions. In: Wang, J., Yi, Z., Zurada, J.M., Lu, BL., Yin, H. (eds) Advances in Neural Networks - ISNN 2006. ISNN 2006. Lecture Notes in Computer Science, vol 3971. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11759966_87
Download citation
DOI: https://doi.org/10.1007/11759966_87
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-34439-1
Online ISBN: 978-3-540-34440-7
eBook Packages: Computer ScienceComputer Science (R0)