Paper Title:
A Comparative Study of Different Neighborhood Topologies in WTM Kohonen Self-Organizing Maps
  Abstract

In this paper we present a software model of the Winner Takes Most (WTM) Kohonen neural network (KNN) with different types of the neighborhood grid. The proposed network model allows for analysis of the convergence properties such as the quantization error and the convergence time for different grids, which is essential looking from the hardware implementation point of view of such networks. Particular grids differ in complexity, which in hardware implementation has a direct influence on power dissipation as well as on chip area and the final production cost. The presented results show that even the simplest rectangular grid with four neighbors allows for good convergence properties for different training data files.

  Info
Periodical
Solid State Phenomena (Volumes 147-149)
Edited by
Zdzislaw Gosiewski and Zbigniew Kulesza
Pages
564-569
DOI
10.4028/www.scientific.net/SSP.147-149.564
Citation
M. Kolasa, R. Długosz, J. Pauk, "A Comparative Study of Different Neighborhood Topologies in WTM Kohonen Self-Organizing Maps", Solid State Phenomena, Vols. 147-149, pp. 564-569, 2009
Online since
January 2009
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Hong Men, Hai Yan Liu, Lei Wang, Yun Peng Pan
Abstract:This paper presents an optimizing method of competitive neural network(CNN):During clustering analysis fixed on the optimum number of output...
894
Authors: Wen Bo Li, Yun Liang Yu, Jian Qiang Wang, Ye Bai, Xin Wang
Chapter 1: Mineral Prospecting and Geological Exploration
Abstract:Studing the identification methods of sedimentary microfacies by the implement of self-organizing neural network model. Picking up the...
38
Authors: Rui Yu, Rui Xiang, Zhi Wu Ke, Shi Wei Yao, Xin Wan
IV. Mechatronics, Control, Automation Technology and Equipment Development
Abstract:A diagnostic method is proposed for the faults of the condenser in the ship steam power system by using the unsupervised learning neural...
1568
Authors: Guang Hui Wang, Qiu Ping Ren
Chapter 9: Measurements, Detection and Fault Diagnosis
Abstract:SOM neural network is of strong non-linearity mapping capacity and flexible network structure. Use this algorithm for training, form a...
1110
Authors: Shuo Ding, Xiao Heng Chang, Qing Hui Wu
Chapter 2: Sensors and Applications
Abstract:Traditional sensor fault diagnosis is mainly based on statistical classification methods. The discriminant functions in these methods are...
193