Abstract
We consider a class of auto-associative memories, namely, “associative cubes” in which gray-level images and the hidden orthogonal basis functions such as Walsh-Hadamard or Fourier kernels, are mixed and updated in the weight cubes, C. First, we develop an unsupervised learning procedure based upon the adaptive recursive algorithm. Here, each 2D training image is mapped into the associated 1D wavelet in the least-squares sense during the training phase. Second, we show how the recall procedure minimizes the recognition errors with a competitive network in the hidden layer. As the images corrupted by noises are applied to an associative cube, the nearest one among the original training images would be retrieved in the sense of the minimum Euclidean squared norm during the recall phase. The simulation results confirm the robustness of associative cubes even if the test data are heavily distorted by noises.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hebb, D.: Organization of Behavior. Science Edition Inc., New York (1961)
Hopfield, J.J.: Neural Networks and Physical Systems with Emergent Collective Computational Abilities. In: Proc. National Academic Sciences USA, Biophysics, vol. 79, pp. 2554–2558 (1982)
Kosko, B.: Bidirectional Associative Memories. IEEE Trans. Syst., Man, Cybern. 18(1), 49–60 (1988)
Kohonen, T.: Self-Organization and Associative Memory. Springer, Heidelberg (1984)
Wang, Y.F., Cruz, J.B., Mulligan Jr., J.H.: Two Coding Strategies for Bi-directional Associative Memory. IEEE Trans. Neural Networks 1, 81–92 (1990)
Kang, H.: Multilayered Associative Neural Networks (M.A.N.N.), Storage Capacity vs. Perfect Recall. IEEE Trans. Neural Networks 5, 812–822 (1994)
Kang, H.: Multilayer Associative Neural Networks: Storage Capacity vs. Noise-free Recall. In: Simpson, P.K. (ed.) IEEE Trans. Neural Network Theory, Technology, and Applications, ser. IEEE Technology Update Series, pp. 215–221. IEEE, New Jersey (1996)
Wang, Y.J., Lee, D.L.: A Modified Bi-directional Decoding Strategy based on the BAM Structure. IEEE Trans. Neural Networks 4, 710–717 (1993)
Lee, D.L., Wang, Y.J.: Neighbor-layer Updating in MBDS for the Recall of Pure Bipolar Patterns in Gray-Scale Noise. IEEE Trans. Neural Networks 6, 1478–1489 (1995)
Burrus, C.S., Gopinath, R.A., Guo, H.: Introduction to Wavelets and Wavelet Transforms. Prentice-Hall International Inc., New Jersey (1998)
Lewis, F.L.: Optimal Estimation. John Wiley & Sons Inc., New York (1986)
Kang, H.: Unsupervised Learning with Associative Cubes for Robust Gray-Scale Image Recognition. In: Proc. ICNN&B 2005, Beijing China (2005)
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
Kang, H. (2006). Associative Cubes in Unsupervised Learning for Robust Gray-Scale Image Recognition. 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 3972. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11760023_86
Download citation
DOI: https://doi.org/10.1007/11760023_86
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-34437-7
Online ISBN: 978-3-540-34438-4
eBook Packages: Computer ScienceComputer Science (R0)