Abstract
A self-creating network effective in learning vector quantization, called RCN (Representation-burden Conservation Network) is developed. Each neuron in RCN is characterized by a measure of representation-burden. Conservation is achieved by bounding the summed representation-burden of all neurons at constant 1, as representation-burden values of all neurons are updated after each input presentation. We show that RCN effectively fulfills the conscience principle [1] and achieves biologically plausible self-development capability. In addition, conservation in representation-burden facilitates systematic derivations of learning parameters, including the adaptive learning rate control useful in accelerating the convergence as well as in improving node-utilization. Because it is smooth and incremental, RCN can overcome the stability-plasticity dilemma. Simulation results show that RCN displays superior performance over other competitive learning networks in minimizing the quantization error.
Similar content being viewed by others
References
S.C. Ahalt, A.K. Krishnamurthy, P. Chen and D. E. Melton, “Competitive learning algorithms for vector quantization,” Neural Networks., Vol. 3, pp. 277–290, 1990.
Y. Matsuyama, “Harmonic competition: a self-organizing multiple criteria optimization,” IEEE Trans. Neural Networks, Vol. 7, No. 3, pp. 652–668, May, 1996.
Y. Linde, A. Buzo and R.M. Gray, “An algorithm for vector quantizer design,” IEEE Trans. Comm., Vol. COM-28, No. 1, pp. 84–95, 1980.
T. Kohonen, Self-Organization and Associative Memory, Springer Series in Information Sciences, Vol. 8. Springer-Verlag, New York, 1984.
S.A. Galanopoulos and S.C. Ahalt, “Codeword distribution for frequency sesitive competitive learning with one-dimensional input data,” IEEE Trans. Neural Networks, Vol. 7, No. 3, pp. 752–756, May, 1996.
S. Haykin, Neural networks, Macmillan College, 1994.
D.I. Choi and S.H. Park, “Self-creating and organizing neural networks,” IEEE Trans. Neural Networks, Vol. 5, No. 4, pp. 561–575, 1994.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Wang, JH., Hsiao, CP. Representation-burden Conservation Network Applied to Learning VQ (NPL270). Neural Processing Letters 5, 209–217 (1997). https://doi.org/10.1023/A:1009651012418
Issue Date:
DOI: https://doi.org/10.1023/A:1009651012418