Skip to main content
SpringerLink
Log in

A Multiagent-Based Constructive Approach for Feedforward Neural Networks

  • Conference paper
Advances in Intelligent Data Analysis V (IDA 2003)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 2810))

Included in the following conference series:

  • 1659 Accesses

Abstract

In this paper, a new constructive approach for the automatic definition of feedforward neural networks (FNNs) is introduced. Such approach (named MASCoNN) is multiagent-oriented and, thus, can be regarded as a kind of hybrid (synergetic) system. MASCoNN centers upon the employment of a two-level hierarchy of agent-based elements for the progressive allocation of neuronal building blocks. By this means, an FNN can be considered as an architectural organization of reactive neural agents, orchestrated by deliberative coordination entities via synaptic interactions. MASCoNN was successfully applied to implement nonlinear dynamic systems identification devices and some comparative results, involving alternative proposals, are analyzed here.

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 84.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
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. Dahmen, W., Micchelli, C.A.: Some remarks on ridge functions. Approximation Theory and its Applications 3(2-3), 139–143 (1987)

    MathSciNet  MATH  Google Scholar 

  2. Davis, P.J.: Interpolation & Approximation. Dover Publications, New York (1975)

    MATH  Google Scholar 

  3. Fahlman, S.E., Lebiere, C.: The cascade-correlation learning architecture. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems, vol. 2, pp. 524–532. Morgan Kaufmann, San Francisco (1990)

    Google Scholar 

  4. Ghosh, J.: Neural-symbolic hybrid systems. In: Padget, M., et al. (eds.) The Handbook of Applied Computational Intelligence. CRC Press, Boca Raton (2001)

    Google Scholar 

  5. Goonatilake, S., Khebbal, S. (eds.): Intelligent Hybrid Systems. Wiley, Chichester (1995)

    Google Scholar 

  6. Härdle, W.: Applied Nonparametric Regression. Cambridge University Press, Cambridge (1990)

    MATH  Google Scholar 

  7. Haykin, S.: Neural Networks–A Comprehensive Foundation. Prentice Hall, Englewood Cliffs (1999)

    MATH  Google Scholar 

  8. Hwang, J., Lay, S., Maechler, M., Martin, D., Schimert, J.: Regression modeling in backpropagation and project pursuit learning. IEEE Trans. on Neural Networks 5(3), 342–353 (1994)

    Article  Google Scholar 

  9. Kwok, T.-Y., Yeung, D.-Y.: Constructive algorithms for structure learning in feedforward neural networks for regression problems. IEEE Trans. on Neural Networks 8(3), 630–645 (1997)

    Article  Google Scholar 

  10. Medskar, L.A.: Hybrid Intelligent Systems. Kluwer Academic Publishers, Dordrecht (1995)

    Google Scholar 

  11. Narendra, K., Parthasarathy, K.: Identification and control of dynamical systems using neural networks. IEEE Trans. on Neural Networks 1(1), 4–27 (1990)

    Article  Google Scholar 

  12. Nrgaard, M., Ravn, O., Poulsen, N.K., Norgaard, P.M., Hansen, L.K.: Neural Networks for Modelling and Control of Dynamic Systems: A Practitioner’s Handbook. In: Advanced Textbooks in Control and Signal Processing. Springer, Heidelberg (2000)

    Google Scholar 

  13. Pham, K.M.: The neurOagent: A neural multi-agent approach for modelling, distributed processing and learning. In: Goonatilake and Khebbal [5], ch. 12, pp. 221–244

    Google Scholar 

  14. Reed, R.: Pruning algorithms–A survey. IEEE Trans. on Neural Networks 4(5), 740–747 (1993)

    Article  Google Scholar 

  15. Scherer, A., Schlageter, G.: A multi-agent approach for the integration of neural networks and expert systems. In: Goonatilake and Khebbal [5], ch. 9, pp. 153–173

    Google Scholar 

  16. Selfridge, O.G.: Pandemonium: A paradigm for learning. In: Proc. Symp. Held Physical Lab.: Mechanisation Thought Processing, pp. 511–517, London (1958)

    Google Scholar 

  17. Śmieja, F.J.: The pandemonium system of reflective agents. IEEE Trans. on Neural Networks 7(1), 97–106 (1996)

    Article  Google Scholar 

  18. Taha, I., Ghosh, J.: Symbolic interpretation of artificial neural networks. IEEE Trans. on Knowledge and Data Eng. 11(3), 448–463 (1999)

    Article  Google Scholar 

  19. Zuben, F.J.V., Netto, M.: Projection pursuit and the solvability condition applied to constructive learning. In: Proc. of the International Joint Conference on Neural Networks, vol. 2, pp. 1062–1067 (1997)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Engineering and Industrial Automation (DCA), Faculty of Electrical and Computer Engineering (FEEC), State University of Campinas (Unicamp), Campinas

    Clodoaldo A. M. Lima, André L. V. Coelho & Fernando J. Von Zuben

Authors
  1. Clodoaldo A. M. Lima
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. André L. V. Coelho
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Fernando J. Von Zuben
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Berkeley Initiative in Soft Computing (BISC), University of California at Berkeley, USA

    Michael R. Berthold

  2. Freie Universität Berlin, Garystr. 21, 14195, Berlin, Germany

    Hans-Joachim Lenz

  3. Department of Computer Science, University of Colorado, Boulder, Colorado, USA

    Elizabeth Bradley

  4. Otto-von-Guericke-University of Magdeburg, Germany

    Rudolf Kruse

  5. Department of Knowledge Processing and Language Engineering, University of Magdeburg, Universitätsplatz 2, 39106, Magdeburg, Germany

    Christian Borgelt

Rights and permissions

Reprints and permissions

Copyright information

© 2003 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Lima, C.A.M., Coelho, A.L.V., Von Zuben, F.J. (2003). A Multiagent-Based Constructive Approach for Feedforward Neural Networks. In: R. Berthold, M., Lenz, HJ., Bradley, E., Kruse, R., Borgelt, C. (eds) Advances in Intelligent Data Analysis V. IDA 2003. Lecture Notes in Computer Science, vol 2810. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45231-7_43

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-45231-7_43

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-40813-0

  • Online ISBN: 978-3-540-45231-7

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation