Modular Network SOM: Theory, Algorithm and Applications
The modular network SOM (mnSOM) proposed by authors is an extension and generalization of a conventional SOM in which each nodal unit is replaced by a module such as a neural network. It is expected that the mnSOM will extend the area of applications beyond that of a conventional SOM. We set out to establish the theory and algorithm of a mnSOM, and to apply it to several research topics, to create a fundamental technology that is generally usable only in expensive studies. In this paper, the theory and the algorithm of the mnSOM are reported; moreover, the results of applications of the mnSOM are presented.
KeywordsRecurrent Neural Network Unsupervised Learning Modular Network Fundamental Technology Kyushu Institute
Unable to display preview. Download preview PDF.
- 1.Kohonen, T.: Self-organizing maps, 3rd edn. Springer, Heidelberg (2003)Google Scholar
- 2.Kohonen, T.: Generalization of the self-organizing map. In: Proc. of International Joint Conference on Neural Networks, pp. 457–462 (1993)Google Scholar
- 3.Tokunaga, K., Furukawa, T., Yasui, S.: Modular network SOM: Extension of SOM to the realm of function space. In: Proc. of Workshop on Self-Organizing Maps, pp. 173–178 (2003)Google Scholar
- 4.Furukawa, T., Tokunaga, K., Morishita, K., Yasui, S.: Modular network SOM(mnSOM): From vector space to function space. In: Proc. of International Joint Conference on Neural Networks, pp. 1581–1586 (2005)Google Scholar
- 5.Kaneko, S., Tokunaga, K., Furukawa, T.: Modular network SOM: The architecture, the algorithm and applications to nonlinear dynamical systems. In: Proc. of Workshop on Self-Organizing Maps, pp. 537–544 (2005)Google Scholar