Variable-Sized Kohonen Feature Map Probabilistic Associative Memory

  • Hiroki Sato
  • Yuko Osana
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7553)


In this paper, we propose a Variable-sized Kohonen Feature Map Probabilistic Associative Memory (VKFMPAM). The proposed model can realize the probabilistic association for the training set including one-to-many relations, and neurons can be added in the Map Layer if necessary. We carried out a series of computer experiments and confirmed the effectiveness of the proposed model.


Self-Organizing Map (Kohonen Feature Map) Probabilistic Association Successive Learning One-to-Many Associations 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kohonen, T.: Self-Organizing Maps. Springer (1994)Google Scholar
  2. 2.
    Ichiki, H., Hagiwara, M., Nakagawa, M.: Kohonen feature maps as a supervised learning machine. In: ICNN, pp. 1944–1948 (1993)Google Scholar
  3. 3.
    Yamada, T., Hattori, M., Morisawa, M., Ito, H.: Sequential learning for associative memory using Kohonen feature map. In: IJCNN, Washington D.C. (1999)Google Scholar
  4. 4.
    Abe, H., Osana, Y.: Kohonen feature map associative memory with area representation. In: IASTED AIA, Innsbruck (2006)Google Scholar
  5. 5.
    Noguchi, S., Osana, Y.: Improved Kohonen feature map probabilistic associative memory based on weights distribution. In: IJCNN, Barcelona (2010)Google Scholar
  6. 6.
    Imabayashi, T., Osana, Y.: Variable-sized KFM associative memory with refractoriness based on area representation. In: SMC, San Antonio (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Hiroki Sato
    • 1
  • Yuko Osana
    • 1
  1. 1.Tokyo University of TechnologyHachiojiJapan

Personalised recommendations