MODULAR NETWORK SOM (MNSOM): A NEW POWERFUL TOOL IN NEURAL NETWORKS
Abstract
In this paper, a new powerful method in artificial neural networks, called modular network SOM (mnSOM) is introduced. mnSOM is a generalization of Self Organizing Maps (SOM) formed by replacing each vector unit of SOM with function module. The modular function could be a multi layer perceptron, a recurrent neural network or even SOM itself. Having this flexibility, mnSOM becomes a new powerful tool in artificial neural network.
Full Text:
PDFReferences
. T. Kohonen, “Self-Organizing Maps,” Springer, 1995
. K. Tokunaga, T. Furukawa, and S. Yasui, ''Modular Network SOM: Extension of SOM to the realm of function space," Proc. of Workshop on Self Organizing Maps (WSOM2003)}, pp. 173-178, 2003.
. T. Furukawa, K. Tokunaga, S. Kaneko, K. Kimotsuki, and S. Yasui, ''Generalized self-organizing maps (mnSOM) for dealing with dynamical systems," Proc. of 2004 International Symposium on Nonlinear Theory and Its Application (NOLTA2004), Fukuoka, Japan, pp. 231-234, 2004.
. M. Aziz Muslim, M. Ishikawa, and T. Furukawa, ''A New Approach to Task Segmentation in Mobile Robots by mnSOM," Proc. of 2006 IEEE World Congress on Computational Intelligence (IJCNN2006 Section), pp. 6542-6549, Vancouver, Canada, 2006.
. M. Aziz Muslim, M. Ishikawa, and T. Furukawa, ''Task Segmentation in a Mobile Robot by mnSOM : A New Approach To Training Expert Modules," Neural Computing and Application, vol. 16, pp. 571-580, Springer, 2007.
. M. Aziz Muslim, M. Ishikawa, and T. Furukawa, ”Task Segmentation in a Mobile Robot by mnSOM and Hierarchical Clustering,” International Workshop on Self-Organizing Maps (WSOM) 2007, Bielefeld, Germany, 2007
. M. Aziz Muslim, Masumi Ishikawa, Tetsuo Furukawa, “Task Segmentation in a Mobile Robot by mnSOM and Clustering with Spatio-temporal Contiguity”, International Journal of Innovative Computing, Information and Control (ICIC), ISSN 1349-4198,
Volume 5, Number 4, April 2009.
. M. Aziz Muslim, Masumi Ishikawa, “Formation of Graph-based Maps for Mobile Robots using Hidden Markov Models”, Proc. of 2008 IEEE World Congress on Computational Intelligence (IJCNN2008 Section), Hongkong, 2008.
. S. Nishida, K. Ishii, and T. Furukawa, “An Online Adaptation Control System Using mnSOM”, Lecture Notes in Computer Science(Edited book of 13th International Conference of Neural Information Processing (ICONIP2006)), Vol.4232, pp.935-942, 2006.
. T. Furukawa, “SOM2 as "SOM of SOMs",” Proceedings of the 5th Workshop on Self-Organizing Maps (WSOM05), pp.41-48, France, 2005.
. T. Furukawa, “Modular Network SOM and Self-Organizing Homotopy Network as a Foundation for Brain-like Intelligence,” 6th Int. Workshop on Self-Organizing Maps (WSOM 2007), Bielefeld/Germany, September 3-6th 2007 (Keynote Speech).
. J. Jiang, L. Zhang, and T. Furukawa,” Improving the Generalization of Fisherface by Training Class Selection Using SOM2,” Lecture Notes in Computer Science(Edited book of 13th International Conference of Neural Information Processing (ICONIP2006)) , Vol.4233, pp.278-285, 2006.
. T. Minatohara, T. Furukawa,” Self-Organizing Adaptive Controllers: Application to the Inverted Pendulum,” Proceedings of the 5th Workshop on Self-Organizing Maps (WSOM05), France, 2005.
DOI: http://doi.org/10.12928/telkomnika.v7i3.590
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
TELKOMNIKA Telecommunication, Computing, Electronics and Control
ISSN: 1693-6930, e-ISSN: 2302-9293
Universitas Ahmad Dahlan, 4th Campus
Jl. Ringroad Selatan, Kragilan, Tamanan, Banguntapan, Bantul, Yogyakarta, Indonesia 55191
Phone: +62 (274) 563515, 511830, 379418, 371120
Fax: +62 274 564604