Abstract
A novel learning algorithm for pattern association in a recurrent neural network is proposed in this paper. Unlike the conventional model in which the memory is stored in an attractive fixed point at discrete location in state space, the dynamics of the proposed learning algorithm represents memory as a line of attraction. The region of convergence at the line of attraction is defined by the statistical characteristics of training data. The performance of the learning algorithm is compared with Bayesian model in experiments on skin color segmentation.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Bengio, Y., Bengio, S., Cloutier, J.: Learning a Synaptic Learning Rule. In: Proc. IEEE Int. Conf. Neural Networks, Seattle Washington, vol. 2, pp. 969–974 (1991)
Seow, M.J., Asari, K.V.: Associative Memory Using Ratio Rule for Multi-Valued Pattern Association. In: Proc. IEEE Int. Conf. Neural Networks, Portland Oregon, vol. 4, pp. 2518–2522 (2003)
Seow, M.J., Asari, K.V.: Learning Using Distance Based Training Algorithm for Pattern Recognition. Pat. Recogn. Let. 25, 189–196 (2004)
Haykin, S.: Neural Network: A Comprehensive Foundation. Macmillan, New York (2001)
Müezzinoglu, M.K., Güzelis, C., Zurada, J.M.: A New Design Method for the Complex- Valued Multistate Hopfield Associative Memory. IEEE Trans. Neural Networks 14, 891–899 (2003)
Brody, C.D., Kepecs, R.A.: Basic Mechanisms for Graded Persistent Activity: Discrete Attractors, Continuous Attractors, and Dynamic Representations. Curr. Opin. Neurobiol. 13, 204–211 (2003)
Stringer, S.M., Trappenberg, T.P., Rolls, E.T., de Araujo, I.E.T.: Self-Organizing Continuous Attractor Networks and Path Integration: One-Dimensional Models of Head Direction Cells. Network: Comput. Neural Syst. 13, 217–242 (2002)
Seung, H.S.: Continuous Attractors and Oculomotor Control. Neural Networks 11, 1253–1258 (1998)
Seow, M.J., Valaparla, D.P., Asari, K.V.: L2-Norm Approximation Based Learning in Recurrent Neural Networks for Expression Invariant Face Recognition. In: Proc. IEEE Int. Conf. System, Man & Cybernetics, Washington DC, pp. 3512–3517 (2003)
Seow, M.J., Asari, K.V.: Associative Memory Based on Ratio Learning for Real Time Skin Region Extraction. In: Proc. IEEE Int. Work. Applied Imagery and Pattern Recognition, Washington DC, pp. 151–156 (2003)
Brand, J.D., Mason, J.S.D.: A Skin Probability Map and Its Use in Face Detection. In: Proc. Int. Conf. Image Processing, Thessaloniki Greece, vol. 1, pp. 1034–1037 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Seow, MJ., Asari, V.K. (2004). Recurrent Network as a Nonlinear Line Attractor for Skin Color Association. In: Yin, FL., Wang, J., Guo, C. (eds) Advances in Neural Networks – ISNN 2004. ISNN 2004. Lecture Notes in Computer Science, vol 3173. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-28647-9_143
Download citation
DOI: https://doi.org/10.1007/978-3-540-28647-9_143
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22841-7
Online ISBN: 978-3-540-28647-9
eBook Packages: Springer Book Archive