Advertisement

Generalization of the Self-Organizing Map: From Artificial Neural Networks to Artificial Cortexes

  • Tetsuo Furukawa
  • Kazuhiro Tokunaga
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4232)

Abstract

This paper presents a generalized framework of a self-organizing map (SOM) applicable to more extended data classes rather than vector data. A modular structure is adopted to realize such generalization; thus, it is called a modular network SOM (mnSOM), in which each reference vector unit of a conventional SOM is replaced by a functional module. Since users can choose the functional module from any trainable architecture such as neural networks, the mnSOM has a lot of flexibility as well as high data processing ability. In this paper, the essential idea is first introduced and then its theory is described.

Keywords

Principle Component Analysis Functional Module Radial Basis Function Network Neighborhood Function Jordan Type 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Tokunaga, K., Furukawa, T., Yasui, S.: Modular network SOM: Extension of SOM to the realm of function space. In: Proc. of WSOM 2003, pp. 173–178 (2003)Google Scholar
  2. 2.
    Tokunaga, K., Furukawa, T., Yasui, S.: Modular network SOM: Self-organizing maps in function space. Neural Information Processing – Letters and Reviews 9(1), 15–22 (2005)Google Scholar
  3. 3.
    Furukawa, T., Tokunaga, K., Morishita, K., Yasui, S.: Modular network SOM (mnSOM): From vector space to function space. In: Proc. of IJCNN 2005, pp. 1581–1586 (2005)Google Scholar
  4. 4.
    Tokunaga, K., Furukawa, T.: Modular network SOM: Theory, algorithm and applications. In: King, I., Wang, J., Chan, L.-W., Wang, D. (eds.) ICONIP 2006. LNCS, vol. 4232, pp. 958–967. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  5. 5.
    Furukawa, T., Tokunaga, K., Kaneko, S., Kimotsuki, K., Yasui, S.: Generalized self-organizing maps (mnSOM) for dealing with dynamical systems. In: Proc. of NOLTA 2004, pp. 231–234 (2004)Google Scholar
  6. 6.
    Kaneko, S., Tokunaga, K., Furukawa, T.: Modular network SOM: The architecture, the algorithm and applications to nonlinear dynamical systems. In: Proc. of WSOM 2005, pp. 537–544 (2005)Google Scholar
  7. 7.
    Tokunaga, K., Furukawa, T.: Nonlinear ASSOM constituted of autoassociative neural modules. In: Proc. of WSOM 2005, pp. 637–644 (2005)Google Scholar
  8. 8.
    Tokunaga, K., Furukawa, T.: Realizing the nonlinear adaptive subspace SOM (NL-ASSOM). In: Proc. of BrainIT 2005, p. 76 (2005)Google Scholar
  9. 9.
    Furukawa, T.: SOM2 as “SOM of SOMs”. In: Proc. of WSOM 2005, pp. 545–552 (2005)Google Scholar
  10. 10.
    Furukawa, T.: SOM of SOMs: Self-organizing map which maps a group of self-organizing maps. In: Duch, W., Kacprzyk, J., Oja, E., Zadrożny, S. (eds.) ICANN 2005. LNCS, vol. 3696, pp. 391–396. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  11. 11.
    Furukawa, T.: SOM of SOMs: An extension of SOM from ‘map’ to ‘homotopy’. In: King, I., Wang, J., Chan, L.-W., Wang, D. (eds.) ICONIP 2006. LNCS, vol. 4232, pp. 950–957. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  12. 12.
    Kohonen, T.: Generalization of the Self-organizing map. In: Proc. of IJCNN 1993, pp. 457–462 (1993)Google Scholar
  13. 13.
    Kohonen, T., Kaski, S., Lappalainen, H.: Self-organized formation of various invariantfeature filters in the adaptive-subspace SOM. Neural Computation 9, 1321–1344 (1997)CrossRefGoogle Scholar
  14. 14.
    Kohonen, T.: Self-Organizing Maps, 3rd edn. Springer, Heidelberg (2001)MATHGoogle Scholar
  15. 15.
    Aziz Muslim, M., Ishikawa, M., Furukawa, T.: A new approach to task segmentation in mobile robots by mnSOM. In: Proc. of IJCNN 2006 (2006)Google Scholar
  16. 16.
    Aziz Muslim, M., Ishikawa, M., Furukawa, T.: Task segmentation in a mobille robot by mnSOM: A new approach to training expert modules. In: Proc. of ICONIP 2006 (2006)Google Scholar
  17. 17.
    Minatohara, T., Furukawa, T.: Self-organizing adaptive controllers: Application to the inverted pendulum. In: Proc. of WSOM 2005, pp. 41–48 (2005)Google Scholar
  18. 18.
    Minatohara, T., Furukawa, T.: A proposal of self-organizing adaptive controller (SOAC). In: Proc. of BrainIT 2005, p. 56 (2005)Google Scholar
  19. 19.
    Nishida, S., Ishii, K.: An adaptive controller system using mnSOM. In: Proc. of BrainIT 2005, p. 85 (2005)Google Scholar
  20. 20.
    Nishida, S., Ishii, K.: An adaptive neural network control system using mnSOM. In: Proc. of OCEANS 2006 (2006) (in press)Google Scholar
  21. 21.
    Nishida, S., Ishii, K.: An Online Adaptation Control System using mnSOM. In: King, I., Wang, J., Chan, L.-W., Wang, D. (eds.) ICONIP 2006. LNCS, vol. 4232, pp. 935–942. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  22. 22.
    Horio, K., Suetake, N.: Inverse halfoning based on pattern information and filters constructed by mnSOM. In: Proc. of BrainIT 2005, p. 102 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Tetsuo Furukawa
    • 1
  • Kazuhiro Tokunaga
    • 1
  1. 1.Kyushu Institute of TechnologyKitakyushuJapan

Personalised recommendations