Paper:

# Reduction Models in Competitive Learning Founded on Distortion Standards

## Michiharu Maeda^{*}, Noritaka Shigei^{**}, Hiromi Miyajima^{**},

and Kenichi Suzaki^{*}

^{*}Department of Computer Science and Engineering, Faculty of Information Engineering, Fukuoka Institute of Technology, 3-30-1 Wajiro-higashi, Higashi-ku, Fukuoka 811-0295, Japan

^{**}Department of Electrical and Electronic Engineering, Faculty of Engineering, Kagoshima University, 1-21-40 Korimoto, Kagoshima 890-0065, Japan

Two reductions in competitive learning founded on distortion standards are discussed from the viewpoint of generating necessary and appropriate reference vectors under the condition of their predetermined number. The first approach is termed the segmental reduction and competitive learning algorithm. The algorithm is presented as follows: First, numerous reference vectors are prepared and the algorithm is processed under competitive learning. Next, reference vectors are sequentially eliminated to reach their prespecified number based on the partition error criterion. The second approach is termed the general reduction and competitive learning algorithm. The algorithm is presented as follows: First, numerous reference vectors are prepared and the algorithm is processed under competitive learning. Next, reference vectors are sequentially erased based on the average distortion criterion. Experimental results demonstrate the effectiveness of our approaches compared to conventional techniques in average distortion. The two approaches are applied to image coding to determine their feasibility in quality and computation time.

*J. Adv. Comput. Intell. Intell. Inform.*, Vol.12, No.3, pp. 314-323, 2008.

- [1] S. Grossberg, “Adaptive pattern classification and universal recoding: I. Parallel development and coding of neural feature detectors,” Biol. Cybern. Vol.23, pp. 121-134, 1976.
- [2] D. J. Willshaw and C. von der Malsburg, “How patterned neural connections can be set up by self-organization,” Proc. R. Soc. Lond. B., Vol.194, pp. 431-445, 1976.
- [3] J. Hertz, A. Krogh, and R.G. Palmer, “Introduction to the theory of neural computation,” Addison-Wesley, 1991.
- [4] S. I. Gallant, “Neural network learning and expert systems,” The MIT Press, 1993.
- [5] T. Kohonen, “Self-organization and associative memory,” Springer-Verlag Berlin, 1989.
- [6] H.-U. Bauer and K. R. Pawelzik, “Quantifying the neighborhood preservation of self-organizing feature maps,” IEEE Trans. Neural Networks, Vol.3, No.4, pp. 570-579, 1992.
- [7] H. Ritter, T. Martinetz, and K. Schulten, “Neural computation and self-organizing maps: An introduction,” Addison-Wesley, 1992.
- [8] T. Martinetz and K. Schulten, “Topology representing networks,” Neural Networks, Vol.7, No.3, pp. 507-522, 1994.
- [9] T. Villmann, M. Herrmann, and T. M. Martinetz, “Topology preservation in self-organizing feature maps: Exact definition and measurement,” IEEE Trans. Neural Networks, Vol.8, No.2, pp. 256-266, 1997.
- [10] M. Maeda, H. Miyajima, and N. Shigei, “Parallel learning model and topological measurement for self-organizing maps,” Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.11, No.3, pp. 327-334, 2007.
- [11] E. Berglund and J. Sitte, “The parameterless self-organizing map algorithm,” IEEE Trans. Neural Networks, Vol.17, No.2, pp. 305-316, 2006.
- [12] Y. Linde, A. Buzo, and R. M. Gray, “An algorithm for vector quantizer design,” IEEE Trans. Commun., Vol.28, No.1, pp. 84-95, 1980.
- [13] H. Ritter and K. Schulten, “On the stationary state of Kohonen’s self-organizing sensory mapping,” Biol. Cybern., Vol.54, pp. 99-106, 1986.
- [14] H. Ritter and K. Schulten, “Convergence properties of Kohonen’s topology conserving maps, Fluctuations, stability, and dimension selection,” Biol. Cybern., Vol.60, pp. 59-71, 1988.
- [15] T. M. Martinetz, S. G. Berkovich, and K. J. Schulten, ““Neural-gas” network for vector quantization and its application to time-series prediction,” IEEE Trans. Neural Networks, Vol.4, No.4, pp. 558-569, 1993.
- [16] N. Shigei, H. Miyajima, and M. Maeda, “Competitive learning with fast neuron-insertion,” Journal of Advanced Computational Intelligence and Intelligent Informatics, Vol.9, No.6, pp. 590-598, 2005.
- [17] M. Maeda, N. Shigei, and H. Miyajima, “Construction of competitive learning by reduction with distortion standards,” Proc. Int. Conf. Intelligent Technologies, pp. 45-52, 2006.
- [18] B. Fritzke, “Growing cell structures –A self-organizing network for unsupervised and supervised learning,” Neural Networks, Vol.7, No.9, pp. 1441-1460, 1994.
- [19] 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.
- [20] H. Xiong, M. N. S. Swamy, M. O. Ahmad, and I. King, “Branching competitive learning network: a novel self-creating model,” IEEE Trans. Neural Networks, Vol.15, No.2, pp. 417-429, 2004.
- [21] J. G. Rodriguez, A. Angelopoulou, and A. Psarrou, “Growing neural gas (GNG): a soft competitive learning method for 2D hand modeling,” IEICE Trans. Inf. & Syst., Vol.E89-D, No.7, pp. 2124-2131, 2006.
- [22] Y.-J. Zhang and Z.-Q. Liu, “Self-splitting competitive learning: a new on-line clustering paradigm,” IEEE Trans Neural Networks, Vol.13, No.2, pp. 369-380, 2002.
- [23] M. Maeda, H. Miyajima, and S. Murashima, “Construction of selforganizing algorithms for vector quantization,” EEJ Scripta Technica, John Wiley & Sons, Vol.127, No.1, pp. 47-55, 1999.
- [24] L. E. Reichl, “A modern course in statistical physics,” University of Texas Press, 1980.
- [25] H. Imai, “Information theory,” Shokodo, 1984.
- [26] A. Gersho and R. M. Gray, “Vector quantization and signal compression,” Kluwer Academic Publishers, 1992.

This article is published under a Creative Commons Attribution-NoDerivatives 4.0 Internationa License.