Abstract
In this paper we propose a multivaluated recurrent neural network for vector quantization where the synaptic potential is given by a weighted sum of values of a function that evaluates the consensus between the states of the process units. Each process unit presents the state with the largest activation potential, that is, it depends on the state of the nearest process units (more strongly connected according to the synaptic weights). Like Hopfield network, it uses a computational energy function that always decreases (or remains constant) as the system evolves according to its dynamical rule based on an energy function that is equivalent to the distortion function of the vector quantization problem. It does not use tuning parameters and so it attains computational efficiency.
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
Ahalt S.C., Krishnamurphy A.C., Chen P., and Mellon D.E. Competitive learning algorithms for vector quantization. Neural Networks, 3 (1990) 277–290.
Anderson, E., The IRISes of the Gaspe Peninsula. Bulletin of the American IRIS Society, 59 (1939) 2–5
Dony R.D.. and Haykin S. Neural Networks approaches to image compression. Proceeding of the IEEE, 83(2) (1995) 288–303.
R. Duda and P. Hart, Pattern Classification and Scene Analysis. New York: Wiley, 1973.
Gersko A. and Gray R.M. Vector Quantization. Kluwer Academic Publishers (1992.
Gray R.M. Vector Quantization and signal compression IEEE ASSSP Magazine, 1 (1980) 4–29.
Linde Y., Buzo A., and Gray R.M. An algorithm for vector quantizer design. IEEE Trans. on Communication, 28(1) (1980) 84–95.
Lloyd, S.P. Least squares quantization in PCM’s. Bell Telephone Laboratories Paper. Murray Hill, NJ, (1957).
Mao J. and Jain A.K. A self-organizing network for hyperellipsoidal clustering (HEC). IEEE Trans. Neural Networks, 7 (1996) 16–29.
Uchiyama T. and Arbib M.A. Color image segmentation using competitive learning. IEEE Trans. on Pattern Analysis and Machine Intelligence, 16(12) (1994) 1197–1206.
Ueda, N., and Nakano R. A new competitive learning approach based on a equidistorsion principle for designing optimal vector quantizers. Neural Networks, 7(8) (1980) 1211–1227.
Zahid, N., Abouelala, O., Limouri, M. Essaid, A. Unsupervised fuzzy clustering. Pattern Recognition Letters., 20 (1999) 123–129.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Benítcz-Ftochcl, R., Muñoz-Pérez, J., Mérida-Casermeiro, E. (2003). A Recurrent Multivalued Neural Network for codebook generation in Vector Quantization. In: Mira, J., Álvarez, J.R. (eds) Computational Methods in Neural Modeling. IWANN 2003. Lecture Notes in Computer Science, vol 2686. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44868-3_38
Download citation
DOI: https://doi.org/10.1007/3-540-44868-3_38
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40210-7
Online ISBN: 978-3-540-44868-6
eBook Packages: Springer Book Archive