Advertisement

Parallel Genetic Algorithms for Architecture Optimization of Neural Networks for Pattern Recognition

  • Martha Cárdenas
  • Patricia Melin
  • Laura Cruz
Part of the Studies in Computational Intelligence book series (SCI, volume 312)

Abstract

This Paper presents the Architecture optimization of Neural Networks using parallel Genetic Algorithms for pattern recognition based on person faces. The optimization consists in obtaining the best architecture in layers, neurons per layer, and achieving the less recognition error in a shorter training time using parallel programming techniques to exploit the resources of a machine with a multi-core architecture. We show the obtained performance by comparing results of the training stage for sequential and parallel implementations.

Keywords

Neural Network Genetic Algorithm Multicore Processor Simple Genetic Algorithm Architecture Optimization 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Alba, E., Nebro, A., Troya, J.: Heterogeneous Computing and Parallel Genetic Algorithms. Journal of Parallel and Distributed Computing 62, 1362–1385 (2002)zbMATHCrossRefGoogle Scholar
  2. 2.
    Bertona, L.: Neural Network training based on Evolutionary Algorithms, Engineering Thesis, Universidad de Buenos Aires (2005)Google Scholar
  3. 3.
    Burger, T.W.: Intel Multi-Core Processors: Quick Reference Guide, http://cachewww.intel.com/cd/00/00/20/57/205707_205707.pdf
  4. 4.
    Cantu-Paz, E.: Efficient and Accurate Parallel Genetic Algorithms. Kluwer Academic Publishers, Dordrecht (2001)Google Scholar
  5. 5.
    Cárdenas, M., Tapia, J., Montiel, O., Sepúlveda, R.: Neurofuzzy system implementation in Multicore Processors, IV Regional Academic Encounter, CITEDI-IPN (2008)Google Scholar
  6. 6.
    Castillo, O., Melin, P.: Hybrid intelligent systems for time series prediction using neural networks, fuzzy logic and fractal theory. IEEE Transactions on Neural Networks 13(6) (2002)Google Scholar
  7. 7.
    Chai, L., Gao, Q., Panda, D.K.: Understanding the Impact of Multi-Core Architecture in Cluster Computing: A Case Study with Intel Dual-Core System. In: The 7th IEEE International Symposium on Cluster Computing and the Grid, CCGrid 2007 (2007)Google Scholar
  8. 8.
    Coello, C.A., Lamont, G.B., Van Veldhuizen, D.A.: Evolutionary Algorithms for Solvin Multi-Objective Problem. Springer, Heidelberg (2004)Google Scholar
  9. 9.
    The Database of Faces, Cambridge University Computer Laboratory, http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html
  10. 10.
    Dongarra, J., Foster, I., Fox, G., Gropp, W., Kennedy, K., Torczon, L., White, A.: Sourcebook of Parallel Computing. Morgan Kaufmann Publishers, San Francisco (2003)Google Scholar
  11. 11.
    Domeika, M., Kane, L.: Optimization Techniques for Intel Multi-Core Processors, http://softwarecommunity.intel.com/articles/eng/2674.htm
  12. 12.
    González, S.: Optimization of Artificial Neural Network Architectures for time series prediction using Parallel Genetic Algorithms. Ms. Thesis (2007)Google Scholar
  13. 13.
    Haupt, R.L., Haupt, S.E.: Practical Genetic Algorithms. Wiley-Interscience, Chichester (2004)zbMATHGoogle Scholar
  14. 14.
    Hornik, K.: Some new results on neural network approximation. Neural Networks 6, 1069–1072 (1993)CrossRefGoogle Scholar
  15. 15.
    Jeffrey, A., Oklobdzija, V.: The computer Engineering Handbook, Digital Systems and Aplications, segunda edicion. CRC press, Boca Raton (1993)Google Scholar
  16. 16.
    Kouchakpour, P., Zaknich, A., Bräunl, T.: Population Variation in Genetic Programming. Elsevier Science Inc., Amsterdam (2007)Google Scholar
  17. 17.
    Melin, P., Castillo, O.: Hybrid Intelligent Systems for Pattern Recognition using Soft Computing: An Evolutionary Approach for Neural Networks and Fuzzy Systems. Springer, Heidelberg (2005)zbMATHGoogle Scholar
  18. 18.
    Melin, P., Castillo, O.: Hybrid Intelligent Systems for Pattern Recognition Using Soft Computing. Springer, Heidelberg (2005)zbMATHGoogle Scholar
  19. 19.
    Mitchell, M.: An introduction to genetic algorithms. MIT Press, Cambridge, ISBN-10: 0-262-63185-7Google Scholar
  20. 20.
    Nowostawski, M., Poli, R.: Parallel Genetic Taxonomy. In: KES 1999, May 13 (1999) (submitted for publication)Google Scholar
  21. 21.
    Ross, A., Nandakumar, K., Jainet, A.K.: Handbook of Multibiometrics. Springer, Heidelberg (2006)Google Scholar
  22. 22.
    Sahab, M.G., Toropov, V., Ashour, A.F.: A Hybrid Genetic Algorithm For Structural Optimization Problems. Asian journal of civil Engineering, 121–143 (2004)Google Scholar
  23. 23.
    Saldivar, P.: Control of a Mechanical Arm Through Soft Computing Techniques. Ms. Thesis, CITEDI-IPN (2006)Google Scholar
  24. 24.
    Salinas, R.: Neural Network Architecture Parametric Face Recognition, Paper, University of Santiago of Chile, pp. 5–9 (2000), http://cabierta.uchile.cl/revista/17/articulos/paper4/index.html
  25. 25.
    Serrano, R.: Multicore computing applied to Genetic Algorithms. Ms. Thesis, CITEDI-IPN (2008)Google Scholar
  26. 26.
    Shorlemmer, M.: Basic Tutorial of Neural Networks. In: Artificial Intelligence Research Institute, Barcelona, Spain (1995)Google Scholar
  27. 27.
    Soto Castro, M.: Face and Voice Recognition in real time using Artificial Neural Networks, Tijuana Institute of Technology, Ms. Thesis (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Martha Cárdenas
    • 1
  • Patricia Melin
    • 1
  • Laura Cruz
    • 1
  1. 1.Tijuana Institute of TechnologyTijuanaMéxico

Personalised recommendations