Selective Weight Update for Neural Network – Its Backgrounds

  • Yoshitsugu Kakemoto
  • Shinichi Nakasuka
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8210)


VSF–Network, Vibration Synchronizing Function Network, is a hybrid neural network combining Chaos Neural Network and hierarchical neural network. VSF–Network is designed for symbol learning. VSF–Network finds unknown parts of input data by comparing to stored pattern and it learns unknown patterns using unused part of the network. New patterns are learned incrementally and they are stored as sub-networks . Combinations of patterns are represented as combinations of the sub-networks. In this paper, the two theoretical backgrounds of VSF–Network are introduced. At the first, an incremental learning framework with Chaos Neural Networks is introduced. Next, the pattern recognition with the combined with symbols is introduced. From the viewpoints of9 differential topology and mixture distribution, the combined pattern recognition by VSF-Network is explained. Through an experiment, both the incremental learning capability and the pattern recognition with pattern combination are shown.

Index Terms

Incremental learning Chaos Neural network nonlinear dynamics catastrophe theory 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kakemoto, Y., Nakasuka, S.: The dynamics of incremental learning by vsf-network. In: Alippi, C., Polycarpou, M., Panayiotou, C., Ellinas, G. (eds.) ICANN 2009, Part I. LNCS, vol. 5768, pp. 688–697. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  2. 2.
    Kakemoto, Y., Nakasuka, S.: Neural assembly generation by selective connection weight updating. In: Proc. IjCNN 2010 (2010)Google Scholar
  3. 3.
    Inamura, T., Tanie, H., Nakamura, Y.: Proto-symbol development and manipulation in the geometry of stochastic model for motion generation and recognition. Technical Report NC2003-65, IEICE (2003)Google Scholar
  4. 4.
    Chandler, D.: Semiotics for Beginners. Routledge (1995)Google Scholar
  5. 5.
    Giraud-Carrier, C.: A note on the utility of incremental learning. AI Communications 13, 215–223 (2000)zbMATHGoogle Scholar
  6. 6.
    Lin, M., Tang, K., Yao, X.: Incremental learning by negative correlation leaning. In: Proc. of IJCNN 2008 (2008)Google Scholar
  7. 7.
    Aihara, T., Tanabe, T., Toyoda, M.: Chaotic neural networks. Phys. Lett. 144A, 333–340 (1990)CrossRefGoogle Scholar
  8. 8.
    Uchiyama, S., Fujisaki, H.: Chaotic itinerancy in the oscillator neural network without lyapunov functions. Chaos 14, 699–706 (2004)CrossRefGoogle Scholar
  9. 9.
    Hopfield, J.: Neurons with graded response have collective computational properties like those of two-stage neurons. Proceedings of the National Academy of Sciences of U.S.A. 81, 13088–13092 (1984)CrossRefGoogle Scholar
  10. 10.
    Kaneko, K.: Chaotic but regular posi-nega switch among coded attractors by cluster size variation. Phys. Rev. Lett. 63, 219 (1989)MathSciNetCrossRefGoogle Scholar
  11. 11.
    Komuro, M.: A mechanism of chaotic itinerancy in globally coupled maps. In: Dynamical Systems (NDDS 2002) (2002)Google Scholar
  12. 12.
    Cobb, L., Ragade, R.: Applications of catastrophe theory in the behavioral and life. Behavioral Science 79(23), 291 (1978)MathSciNetGoogle Scholar
  13. 13.
    Cobb, L., Watson, B.: Statistical catastrophe theory: An overview. Mathematical Modellin 23(8), 1–27 (1980)MathSciNetGoogle Scholar
  14. 14.
    Thom, R.: Stability and Morphogenesis.: Essai D’une Theorie Generale Des Modeles. W. A. Benjamin, California (1973)Google Scholar
  15. 15.
    Grasman, R., van der Maas, H., Wagenmakers, E.: Journal of statistical software. Mathematical Modelling 32, 1–27 (2009)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Yoshitsugu Kakemoto
    • 1
  • Shinichi Nakasuka
    • 2
  1. 1.The JSOL, LtdChuo-kuJapan
  2. 2.The University of TokyoBunkyo-kuJapan

Personalised recommendations