Neural Computing & Applications

, Volume 1, Issue 1, pp 23–31 | Cite as

Generation and adaptation of neural networks by evolutionary techniques (GANNET)

  • G. E. Robbins
  • M. D. Plumbley
  • J. C. Hughes
  • F. Fallside
  • R. Prager
Articles

Abstract

This paper describes the use of an evolutionary design system known as GANNET to synthesize the structure of neural networks. Initial results are presented for two benchmark problems: the exclusive-or and the two-spirals. A variety of performance criteria and design components are used and comparisons are drawn between the performance of genetic algorithms and other related techniques on these problems.

Keywords

GANNET Genetic algorithms Neural networks Exclusive-or Two-spirals 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Holland JH. Adaptation in natural and artificial systems. University of Michigan Press, Ann Arbor, MI, 1975Google Scholar
  2. 2.
    Montana DJ, Davis L. Training feed-forward neural networks using genetic algorithms. Proceedings of the Eleventh International Conference on Artificial Intelligence; 1989Google Scholar
  3. 3.
    Cressy D. An extended N-tuple approach to speech recognition [MSc Dissertation]. Edinburgh, UK: Univ of Edinburgh, 1988Google Scholar
  4. 4.
    Goldberg DE. Genetic algorithms in search, optimisation, and machine learning. Addison Wesley, New York, NY, 1989Google Scholar
  5. 5.
    Miller GF, Todd PM, Hegde SH. Designing neural networks using genetic algorithms. Proceedings of the Third International Conference on Genetic Algorithms; 1989; Morgan Kaufmann, New York, NYGoogle Scholar
  6. 6.
    Caruana RA, Schaffer JD. Representation and hidden bias: Gray vs binary coding for genetic algorithms. Proceedings of the Fifth International Conference on Machine Learning; 1988; Ann Arbor, MIGoogle Scholar
  7. 7.
    Belew RK, McInerney J, Schraudolph NN. Using the Genetic Algorithm with Connectionist Learning. San Diego (CA): University of California at San Diego; 1990 CSE Technical Report #CS90-174Google Scholar
  8. 8.
    Rumelhart DE, McClelland JL. Parallel distributed processing, explorations in the microstructure of cognition. MIT Press, Cambridge, MA, 1986Google Scholar
  9. 9.
    Lang KJ, Witbrock MJ. Learning to tell two spirals apart. Proceedings of the 1988 Connectionist Models Summer School; 1988; Morgan Kaufmann, New York, NYGoogle Scholar
  10. 10.
    Schraudolph NN, Belew RK. Dynamic parameter encoding for genetic algorithms. San Diego (CA): University of California at San Diego; 1990 CSE Technical Report #CS 90-175Google Scholar
  11. 11.
    Nguyen DH, Widrow B. Neural networks for self-learning control systems. IEEE Control Syst Mag 1990 Apr, 18–23Google Scholar
  12. 12.
    Harp SA, Samad T, Guha A. Towards the genetic synthesis of neural networks. Proceedings of the Third International Conference on Genetic Algorithms; 1989; Morgan Kaufmann, New York, NYGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1993

Authors and Affiliations

  • G. E. Robbins
    • 1
  • M. D. Plumbley
    • 2
  • J. C. Hughes
    • 1
  • F. Fallside
    • 2
  • R. Prager
    • 2
  1. 1.Logica Cambridge LtdCambridgeUK
  2. 2.Cambridge University Engineering DepartmentCambridgeUK

Personalised recommendations