JOURNAL BROWSE
Search
Advanced SearchSearch Tips
Validity Study of Kohonen Self-Organizing Maps
facebook(new window)  Pirnt(new window) E-mail(new window) Excel Download
 Title & Authors
Validity Study of Kohonen Self-Organizing Maps
Huh, Myung-Hoe;
  PDF(new window)
 Abstract
Self-organizing map (SOM) has been developed mainly by T. Kohonen and his colleagues as a unsupervised learning neural network. Because of its topological ordering property, SOM is known to be very useful in pattern recognition and text information retrieval areas. Recently, data miners use Kohonen´s mapping method frequently in exploratory analyses of large data sets. One problem facing SOM builder is that there exists no sensible criterion for evaluating goodness-of-fit of the map at hand. In this short communication, we propose valid evaluation procedures for the Kohonen SOM of any size. The methods can be used in selecting the best map among several candidates.
 Keywords
Kohonen Self-Organizing Map (SOM);Data Mining;Partitioned Data Sets;Valid Measure of Lack-of-Fit;Re-sampling;
 Language
English
 Cited by
 References
1.
Neural Networks, 2002. vol.15. pp.967-978 crossref(new window)

2.
Classification(Second Edition), 1999.

3.
The Elements of Statistical Learning, 2001. pp.480-485

4.
Korean Journal of Applied Statistics, 2003. vol.16. crossref(new window)

5.
Korean Journal of Applied Statistics, 2002. vol.15. pp.252-267 crossref(new window)

6.
Neurocomputing, 1998. vol.21. pp.1-6 crossref(new window)

7.
Self-Organizing Maps, 1995.

8.
Kohonen Maps, 1999. pp.121-129

9.
Pattern Recognition and Neural Network, 1996. pp.322-326