Skip to main content
SpringerLink
Log in

Gannet: Genetic design of a neural net for face recognition

  • Neural Networks
  • Conference paper
  • First Online:
Parallel Problem Solving from Nature (PPSN 1990)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 496))

Included in the following conference series:

Abstract

A system that uses a Genetic Algorithm to specify the structure of a back-propagation type neural net is described. The GA can achieve significant improvements in performance over both random and fully connected nets. The efficacy of the evaluation procedure is demonstrated by showing that the system is able to eliminate a small penalty flag despite the high noise levels.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

8 References

  • Fahlman S. E. Faster-learning variations of back-propagation: an empirical study. In Proceedings of the 1988 Connectionist Models Summer School, D.Touretzky, G.Hinton and T.Sejnowski (Eds), Morgan Kaufmann 1989.

    Google Scholar 

  • Gerrits M. and Hogeweg P. A Genetic Algorithm application on the search for minimal mutation phyletic trees, an NP-complete problem. This volume.

    Google Scholar 

  • Grefenstette J.J and Fitzpatrick J.M. Genetic search with approximate function evaluations. Proceedings of an International Conference on Genetic Algorithms, 1985.

    Google Scholar 

  • Hancock P.J.B. and Smith L.S. Data representation and net structure for object perception. Proceedings of Neuro-Nimes 89. Herault J (Ed).

    Google Scholar 

  • Hancock P.J.B. GANNET: Design of a neural net for face recognition by Genetic Algorithm. In Proceedings of IEEE Workshop on Genetic Algorithms, Neural Networks and Simulated Annealing applied to problems in signal and image processing, Glasgow, May 1990. Also TR-CCCN-6, Dept of Computing Science, University of Stirling.

    Google Scholar 

  • Whitley D. The Genitor project and selection pressure: why rank-based allocation of reproductive trials is best. Proc 3rd International Conference on Genetic Algorithms 1989

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Centre for Cognitive and Computational Neuroscience, University of Stirling, FK9 4LA, UK

    P. J. B. Hancock & Leslie S. Smith

Authors
  1. P. J. B. Hancock
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Leslie S. Smith
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Hans-Paul Schwefel Reinhard Männer

Rights and permissions

Reprints and permissions

Copyright information

© 1991 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Hancock, P.J.B., Smith, L.S. (1991). Gannet: Genetic design of a neural net for face recognition. In: Schwefel, HP., Männer, R. (eds) Parallel Problem Solving from Nature. PPSN 1990. Lecture Notes in Computer Science, vol 496. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0029766

Download citation

  • DOI: https://doi.org/10.1007/BFb0029766

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-54148-6

  • Online ISBN: 978-3-540-70652-6

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation