Skip to main content
SpringerLink
Log in

A Generalized Net Model Based on Fast Learning Algorithm of Unsupervised Art2 Neural Network

  • Conference paper
Intelligent Systems'2014

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 322))

  • 1498 Accesses

Abstract

In this paper the fast learning algorithm of unsupervised adaptive resonance theory ART2 neural network is described. At the beginning of the process the algorithm is illustrated step by step by mathematical formulas and it is shown how individual vector changes its values during the training. The network supports clustering by using competitive learning, normalization and suppression of the noise. At the end of the process we have stable recognition clusters with values according to the vectors.

The learning process algorithm is presented by a Generalized net model.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Atanassov, K.: Generalized nets. World Scientific, Singapore (1991)

    Google Scholar 

  2. Ben, K., van der Smagt, P.: An introduction to Neural Networks, 8th edn., ch. 6. University of Amsterdam (1996)

    Google Scholar 

  3. Carpenter, G., Grossberg, S.: The ART of adaptive pattern recognition by a self-organizing neural network. Computer 21(3), 77–88 (1988)

    Article  Google Scholar 

  4. Grossberg, S., Carpenter, G.: ART2: Self-organization of stable category recognition codes of analog input patterns. Boston University, Center for Adaptive Systems 26(23), 4919–4930 (1987)

    Google Scholar 

  5. Grossberg, S.: Adaptive pattern classification and universal recoding. II. Feedback, expectation, olfacation, and illusions. Bioi. Cybemet. 23, 187–202 (1976)

    MATH  MathSciNet  Google Scholar 

  6. Sivanandam, S., Deepa, S.: Introduction to Neural Networks using matlab 6.0

    Google Scholar 

  7. Fausett, L.: Fundamentals of Neural Networks; Architecture algorithms and applications (1993)

    Google Scholar 

  8. McCulloch, W., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics (1943)

    Google Scholar 

  9. Petkov, T., Sotirov, S.: Generalized net model of the ART1 Neural Network. Annual of “Informatics” Section Union of Scientists in Bulgaria 6, 32–38 (2013)

    Google Scholar 

  10. Petkov, T., Sotirov, S.: Bio-inspired Artificial Intelligence: Generalized Net Model of the Cognitive and Neural Algorithm for Adaptive Resonance Theory 1. Int. J. Bioautomation 17(4), 207–216 (2013)

    Google Scholar 

  11. Petkov, T., Surchev, S., Sotirov, S.: Generalized net model of the forest-fire detection with ART2 neural network. In: International Workshop on Generalized Nets, IWGN 2013 (2013)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Intelligent Systems Laboratory, University of Prof. d-r Assen Zlatarov, Bourgas, Bulgaria

    Todor Petkov & Sotir Sotirov

Authors
  1. Todor Petkov
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sotir Sotirov
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Todor Petkov .

Editor information

Editors and Affiliations

  1. School of Computing and Communications, Lancaster University, Lancaster, United Kingdom

    P. Angelov

  2. Institute of Biophysics and Biomedical Engineering, Bulgarian Academy of Sciences, Sofia, Bulgaria

    K.T. Atanassov

  3. Intelligent Systems Department, Bulgarian Academy of Sciences Inst. of Infor. & Communication Techn., Sofia, Bulgaria

    L. Doukovska

  4. Metalurgy, University of Chemical Technology and, Sofia, Bulgaria

    M. Hadjiski

  5. University of Library Studies and IT (ULSIT), Sofia, Bulgaria

    V. Jotsov

  6. Systems Research Institute, Polish Academy of Sciences, Warsaw, Poland

    J. Kacprzyk

  7. Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, Auckland, New Zealand

    N. Kasabov

  8. Intelligent Systems Laboratory, Prof. Assen Zlatarov University Faculty of Technical Sciences, Bourgas, Bulgaria

    S. Sotirov

  9. Systems Research Institute, Polish Academy of Sciences, Warsaw, Poland

    E. Szmidt

  10. Systems Research Institute, Polish Academy of Sciences, Warsaw, Poland

    S. Zadrożny

Rights and permissions

Reprints and permissions

Copyright information

© 2015 Springer International Publishing Switzerland

About this paper

Cite this paper

Petkov, T., Sotirov, S. (2015). A Generalized Net Model Based on Fast Learning Algorithm of Unsupervised Art2 Neural Network. In: Angelov, P., et al. Intelligent Systems'2014. Advances in Intelligent Systems and Computing, vol 322. Springer, Cham. https://doi.org/10.1007/978-3-319-11313-5_55

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-11313-5_55

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-11312-8

  • Online ISBN: 978-3-319-11313-5

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation