Skip to main content
SpringerLink
Log in

An Evolutionary Approach for Tuning Artificial Neural Network Parameters

  • Conference paper
Hybrid Artificial Intelligence Systems (HAIS 2008)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 5271))

Included in the following conference series:

Abstract

The widespread use of artificial neural networks and the difficult work regarding the correct specification (tuning) of parameters for a given problem are the main aspects that motivated the approach purposed in this paper. This approach employs an evolutionary search to perform the simultaneous tuning of initial weights, transfer functions, architectures and learning rules (learning algorithm parameters). Experiments were performed and the results demonstrate that the method is able to find efficient networks with satisfactory generalization in a shorter search time.

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 139.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 179.00
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. Abraham, A.: Meta learning evolutionary artificial neural networks. Neurocomputing 56, 1–38 (2004)

    Article  Google Scholar 

  2. Almeida, L.M., Ludermir, T.B.: Automatically searching near-optimal artificial neural networks. In: 15th European Symposium on Artificial Neural Networks, pp. 549–554 (2007)

    Google Scholar 

  3. Almeida, L.M., Ludermir, T.B.: An improved method for automatically searching near-optimal artificial neural networks. In: International Joint Conference on Neural Networks (2008)

    Google Scholar 

  4. Cantú-Paz, E., Kamath, C.: An empirical comparison of combinations of evolutionary algorithms and neural networks for classification problems. IEEE Transactions on Systems, Man, and Cybernetics, Part B 35(5), 915–927 (2005)

    Article  Google Scholar 

  5. Eiben, A.E., Smith, J.E.: Introduction to Evolutionary Computing. Springer, Heidelberg (2003)

    MATH  Google Scholar 

  6. Ferentinos, K.P.: Biological engineering applications of feed-forward neural networks designed and parameterized by genetic algorithms. Neural Networks 18(7), 934–950 (2005)

    Article  Google Scholar 

  7. García-Pedrajas, N., Hervás-Martínez, C., Ortiz-Boyer, D.: Cooperative co-evolution of artificial neural network ensembles for pattern classification. IEEE Transaction on Evolutionary Computation 9(3), 271–302 (2005)

    Article  Google Scholar 

  8. García-Pedrajas, N., Ortiz-Boyer, D., Hervás-Mart´ınez, C.: Cooperative co-evolution of generalized multilayer perceptrons. Neurocomputing 56, 257–283 (2004)

    Article  Google Scholar 

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

    MATH  Google Scholar 

  10. Islam, M.M., Murase, K.: A new algorithm to design compact two-hidden-layer artificial neural networks. Neural Networks 14(9), 1265–1278 (2001)

    Article  Google Scholar 

  11. Ma, L., Khorasani, K.: New training strategies for constructive neural networks with application to regression problems. Neural Networks 17(4), 589–609 (2004)

    Article  Google Scholar 

  12. Asuncion, A., Newman, D.: UCI machine learning repository, University of California, Irvine, School of Information and Computer Sciences (2007), http://mlearn.ics.uci.edu/MLRepository.html

  13. Yao, X.: Evolving artificial neural networks. Proceedings of the IEEE 87(9), 1423–1447 (1999)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Center of Informatics, Federal University of Pernambuco, P.O. Box 7851, Cidade Universitária, Recife, PE, Brazil, 50732-970

    Leandro M. Almeida & Teresa B. Ludermir

Authors
  1. Leandro M. Almeida
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Teresa B. Ludermir
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Escuela Politécnica Superior, GICAP Research Group, Universidad de Burgo, Calle Francisco de Vitoria S/N, Edifico C, Campus Vena, 09006, Burgos, Spain

    Emilio Corchado

  2. Center of Excellence for Quantifiable Quality of Service, Norwegian University of Science and Technology, 7491, Trondheim, Norway

    Ajith Abraham

  3. Department of Electrical and Computer Engineering, University of Alberta, Edmonton,, T6G 2V4, Alberta, Canada

    Witold Pedrycz

Rights and permissions

Reprints and permissions

Copyright information

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Almeida, L.M., Ludermir, T.B. (2008). An Evolutionary Approach for Tuning Artificial Neural Network Parameters. In: Corchado, E., Abraham, A., Pedrycz, W. (eds) Hybrid Artificial Intelligence Systems. HAIS 2008. Lecture Notes in Computer Science(), vol 5271. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87656-4_20

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-87656-4_20

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-87655-7

  • Online ISBN: 978-3-540-87656-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation