Efficiency Aspects of Neural Network Architecture Evolution Using Direct and Indirect Encoding

  • H. Kwasnicka
  • M. Paradowski


Using a GA as a NN designing tool deals with many aspects. We must decide, among others, about: coding schema, evaluation function, genetic operators, genetic parameters, etc. This paper focuses on an efficiency of NN architecture evolution. We use two main approaches for neural network representation in the form of chromosomes: direct and indirect encoding. Presented research is a part of our wider study of this problem [1, 2]. We present the influence of coding schemata on the possibilities of evolving optimal neural network.


Neural Network Genetic Algorithm Terminal Symbol Direct Encode Architecture Evolution 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Paradowski M. (2004) Evolution of neural network Architecture Using Genetic Algorithms (in Polish), Master Thesis, Wroclaw University of TechnologyGoogle Scholar
  2. [2]
    Kwasnicka H., Paradowski M. (2004) Selection Pressure and an Efficiency of Neural Network Architecture Evolving, Lecture Notes on Artificial Intelligence, Springer-VerlagGoogle Scholar
  3. [3]
    Goldberg D.E. (1989) Genetic Algorithms in Search, Optimization, and Machine Learning, Addison-Wesley Publishing Company, Inc.Google Scholar
  4. [4]
    Tadeusiewicz R. (1993) Neural networks (in Polish), Akademicka Oficyna Wydawnicza RMGoogle Scholar
  5. [5]
    Yao X. (1999) Evolving Artificial Neural Networks, School of Computer Science, The University of BirminghamGoogle Scholar
  6. [6]
    Balakrishnan K., Honavar V. (1995) Properties of Genetic Representations of Neural Architectures, Proc. of the World Congress on Neural Networks (WCNN’95)Google Scholar
  7. [7]
    Bornholdt S., Graudenz D. (1992) General Asymmetric Neural Networks and Structure Design by Genetic Algorithms, Neural Networks, Vol. 5, pp. 327–334CrossRefGoogle Scholar
  8. [8]
    Stanley K.O., Bryant B.D., Miikkulainen R (2003) Evolving Adaptive Neural Networks with and without Adaptive Synapses, 2003 IEEE Congress on Evolutionary Computation (CEC-2003)Google Scholar
  9. [9]
    Chang S.O., Okurama A.M. (2004) Impedance-Reflecting Teleoperation with a Real-Time Evolving Neural Network ControllerGoogle Scholar
  10. [10]
    Garcia-Pedrajas N., Ortiz-Boyer D., Hervas-Martinez C. (2004) An alternative approach for neural network evolution with a genetic algorithm: Crossover by combinatorial optimization, Preprint submittet to Elsevier ScienceGoogle Scholar
  11. [11]
    Dewri R. (2002) Evolutionary Neural Networks: Design metodologies, AI depot, http://ai-depot.comGoogle Scholar
  12. [12]
    Whitley D. (1995) Genetic Algorithms and Neural Networks, Genetic Algorithms in Engineering and Computer ScienceGoogle Scholar
  13. [13]
    Gruau F. (1994) Neural Network Synthesis Using Cellular Encoding And The Genetic Algorithm, Universite Claude Bernard, LyonGoogle Scholar
  14. [14]
    Perchelt L. (1994) Probenl-A Set of Neural Network Benchmark Problems and Benchmarking Rules, Technical Report 21/94Google Scholar

Copyright information

© Springer-Verlag/Wien 2005

Authors and Affiliations

  • H. Kwasnicka
    • 1
  • M. Paradowski
    • 1
  1. 1.Department of Computer ScienceWroclaw University of TechnologyPoland

Personalised recommendations