Advertisement

A New Method of Multilayer Perceptron Encoding

  • Emmanuel Blindauer
  • Jerzy Korczak
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2723)

4 Conclusion

The experiments have confirmed that, firstly by encoding the network topology and weights the search space is affined; secondly, by the inheritence of connection weights, the learning stage is speeded up considerably. The presented method generates efficient networks in a shorter time compared to actual methods. The new encoding scheme improves the effectiveness of evolutionary process: weights of the neural network included in the genetic encoding scheme and good genetics operators give acceptable results.

Keywords

Neural Network Network Topology Encode Scheme Crossover Operator Learning Stage 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. 1.
    J. Korczak and E. Blindauer, An Approach to Encode Multilayer Perceptrons, [In] Proceedings of the International Conference on Artificial Neural Networks, 2002Google Scholar
  2. 2.
    E. Cantú-Paz, C. Kamath, Evolving Neural Networks For The Classification of Galaxies, [In] Proceedings of the Genetic and Evolutionary Computation Conference, 2002Google Scholar
  3. 3.
    M.A. Grönroos, Evolutionary Design Neural Networks, PhD thesis, Department of Mathematical Sciences, University of Turku, 1998.Google Scholar
  4. 4.
    F. Gruau, Neural networks synthesis using cellular encoding and the genetic algorithm, PhD thesis, LIP, Ecole Normale Superieure, Lyon, 1992.Google Scholar
  5. 5.
    H. Kitano, Designing neural networks using genetic algorithms with graph generation system, Complex Systems, 4: 461–476, 1990.zbMATHGoogle Scholar
  6. 6.
    F. Radlinski, Evolutionary Learning on Structured Data for Artificial Neural Networks, MSC Thesis, Dep. of Computer Science Australian National University, 2002Google Scholar
  7. 7.
    X. Yao, Evolving artificial neural networks. Proceedings of the IEEE, 1999.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Emmanuel Blindauer
    • 1
  • Jerzy Korczak
    • 1
  1. 1.Laboratoire des Sciences de l’Image, de l’Informatique et de la Télédétection, UMR7005CNRSIllkirchFrance

Personalised recommendations