Skip to main content
Springer Nature Link
Log in

Fuzzy ARTMAP with Explicit and Implicit Weights

  • Conference paper
Neural Information Processing (ICONIP 2007)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 4984))

Included in the following conference series:

  • 1285 Accesses

Abstract

ARTMAP is one of the famous supervised learning systems. Many learning methods for ARTMAP have been proposed since it was devised as a system to solve Stability-Plasticity Dilemma. AL-SLMAP was implemented by slightly modifying FCSR which was the original learning method for fuzzy ARTMAP (FAM). Although AL-SLMAP can solve pattern recognition problems in a noisy environment more effectively than FCSR, AL-SLMAP is less suitable for region classification problems than FCSR. This means that AL-SLMAP has some problems which do not exist in FCSR. In this paper, we propose a learning method for FAM with explicit and implicit weights to overcome the problems.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Carpenter, G.A., Grossberg, S., Markuzon, N., Reynolds, J.H., Rosen, D.B.: Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Trans. Neural Networks 3(5), 698–713 (1992)

    Article  Google Scholar 

  2. Lee, J.S., Yoon, C.G., Lee, C.W.: Improvement of recognition performance for the fuzzy ARTMAP using average learning and slow learning. IEICE Trans. Fundamentals E81-A(3), 514–516 (1998)

    MathSciNet  Google Scholar 

  3. Carpenter, G.A., Grossberg, S., Reynolds, J.H.: A fuzzy ARTMAP nonparametric probability estimator for nonstationary pattern recognition problems. IEEE Trans. Neural Networks 6(6), 1330–1336 (1995)

    Article  Google Scholar 

  4. Kamio, T., Nomura, K., Mori, K., Fujisaka, H., Haeiwa, K.: Improvement of Fuzzy ARTMAP by Controlling Match Tracking. In: Proc. International Symposium on Nonlinear Theory and its Applications, pp. 791–794 (2006)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Dept. of Systems Engineering, Hiroshima City University, 3-4-1, Ozuka-higashi, Asaminami-ku, Hiroshima-shi, Hiroshima, 731-3194, Japan

    Takeshi Kamio, Kenji Mori, Chang-Jun Ahn, Hisato Fujisaka & Kazuhisa Haeiwa

  2. Dept. of Electronics and Computer Systems, Takushoku University, 815-1, Tatemachi, Hachioji-shi, Tokyo, 193-0985, Japan

    Kunihiko Mitsubori

Authors
  1. Takeshi Kamio
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Kenji Mori
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Kunihiko Mitsubori
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chang-Jun Ahn
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Hisato Fujisaka
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Kazuhisa Haeiwa
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Masumi Ishikawa Kenji Doya Hiroyuki Miyamoto Takeshi Yamakawa

Rights and permissions

Reprints and permissions

Copyright information

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kamio, T., Mori, K., Mitsubori, K., Ahn, CJ., Fujisaka, H., Haeiwa, K. (2008). Fuzzy ARTMAP with Explicit and Implicit Weights. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds) Neural Information Processing. ICONIP 2007. Lecture Notes in Computer Science, vol 4984. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69158-7_32

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-69158-7_32

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-69154-9

  • Online ISBN: 978-3-540-69158-7

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics