Abstract
In a recent publication [1], it was shown that a biologically plausible RCN (Representation-burden Conservation Network) in which conservation is achieved by bounding the summed representation-burden of all neurons at constant 1, is effective in learning stationary vector quantization. Based on the conservation principle, a new approach for designing a dynamic RCN for processing both stationary and non-stationary inputs is introduced in this paper. We show that, in response to the input statistics changes, dynamic RCN improves its original counterpart in incremental learning capability as well as in self-organizing the network structure. Performance comparisons between dynamic RCN and other self-development models are also presented. Simulation results show that dynamic RCN is very effective in training a near-optimal vector quantizer in that it manages to keep a balance between the equiprobable and equidistortion criterion.
Similar content being viewed by others
References
J.H. Wang and C.P. Hsiao, “Representation-burden conservation network applied to learning VQ”, Neural Processing Letters, Vol. 5,3, pp. 209–217, 1997.
Y. Linde, A. Buzo and R.M. Gray, “An algorithm for fector quantizer design,” IEEE Trans. Comm., Vol. COM-28, No. 1, pp. 84–95, Jan. 1980.
S.C. Ahalt, A.K. Krishnamurthy, P. Chen and D.E. Melton, “Competitive learning algorithms for fector quantization,” Neural Networks, Vol. 3, pp. 277–290, Oct. 1990.
Y. Matsuyama, “Harmonic competititon: a self-organizing multiple criteria optimization,” IEEE Trans. Neural Networks, Vol. 7, No. 3, pp. 652–668, May 1996.
T. Kohonen, Self-Organization and Associative Memory, Vol. 8 of Springer Series in Information Sciences, Springer-Verlag, New York, 1984.
S.A. Galanopoulos and S.C. Ahalt, “Codeword distribution for frequency sensitive competitive learning with one-dimensional input data,” IEEE Trans. Neural Networks, Vol. 7, No. 3, pp. 752–756, May 1996.
S. Kaykin, Neural Networks, Macmillan College, 1994.
I. Choi and S.H. Park, “Self-creating and organizing neural networks,” IEEE Trans. Neural Networks, Vol. 5, No. 4, pp. 561–575, Jul. 1994.
B. Fritzke, “Growning cell structure: a self-organizing network for unsupervised and supervised learning,” Neural Networks, Vol. 7, No. 9, pp. 1441–1460, 1994.
B. Fritzke, “Growing grid - a self-organizing network with constant neighborhood range and adaption strength”, Neural Processing Letters, Vol. 2, No. 5, pp. 9–13, 1995.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wang, JH., Sun, WD. Improved Representation-burden Conservation Network for Learning Non-stationary VQ. Neural Processing Letters 8, 41–53 (1998). https://doi.org/10.1023/A:1009665029120
Issue Date:
DOI: https://doi.org/10.1023/A:1009665029120