Design of Kohonen Self-organizing Map with Reduced Structure

This paper deals with design of optimal structure of Kohonen Self-organizing maps for cluster analysis applications. The cluster analysis represents a group of methods whose aim is to classify the objects into clusters. There have been many new algorithms solving cluster analysis applications, which used neural networks. This paper deals with the use of advanced methods of neural networks represented by Kohonen self-organizing maps for cluster analysis. For attainment of good results of cluster analysis is necessary to optimize the Kohonen network structure and algorithm parameters. There has been presented an example of a case study in Matlab software, where cluster analysis with optimization of Kohonen network structure and algorithm parameters is used.