Advertisement

Integrated Feature and Parameter Optimization for an Evolving Spiking Neural Network

  • Stefan Schliebs
  • Michaël Defoin-Platel
  • Nikola Kasabov
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5506)

Abstract

This study extends the recently proposed Evolving Spiking Neural Network (ESNN) architecture by combining it with an optimization algorithm, namely the Versatile Quantum-inspired Evolutionary Algorithm (vQEA). Following the wrapper approach, the method is used to identify relevant feature subsets and simultaneously evolve an optimal ESNN parameter setting. Applied to carefully designed benchmark data, containing irrelevant and redundant features of varying information quality, the ESNN-based feature selection procedure lead to excellent classification results and an accurate detection of relevant information in the dataset. Redundant and irrelevant features were rejected successively and in the order of the degree of information they contained.

Keywords

Feature Subset Neural Model Noise Strength Redundant Feature Optimal Feature Subset 
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.
    Maass, W.: Computing with spiking neurons (1999)Google Scholar
  2. 2.
    Verstraeten, D., Schrauwen, B., Stroobandt, D.: Isolated word recognition using a liquid state machine. In: ESANN, pp. 435–440 (2005)Google Scholar
  3. 3.
    Bohte, S.M., Kok, J.N., Poutré, J.A.L.: Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing 48(1-4), 17–37 (2002)CrossRefzbMATHGoogle Scholar
  4. 4.
    Knoblauch, A.: Neural associative memory for brain modeling and information retrieval. Inf. Process. Lett. 95(6), 537–544 (2005)MathSciNetCrossRefzbMATHGoogle Scholar
  5. 5.
    Wysoski, S.G., Benuskova, L., Kasabov, N.: On-line learning with structural adaptation in a network of spiking neurons for visual pattern recognition. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds.) ICANN 2006. LNCS, vol. 4131, pp. 61–70. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  6. 6.
    Wysoski, S., Benuskova, L., Kasabov, N.: Brain-like evolving spiking neural networks for multimodal information processing. In: ICONIP 2007. LNCS. Springer, Heidelberg (2007)Google Scholar
  7. 7.
    Soltic, S., Wysoski, S., Kasabov, N.: Evolving spiking neural networks for taste recognition. In: IEEE World Congress on Computational Intelligence (WCCI), Hong Kong (2008)Google Scholar
  8. 8.
    VanRullen, R., Thorpe, S.J.: Is it a bird? is it a plan? ultra-rapid visual categorisation of natural and artificial objects. Perception 30, 655–668 (2001)CrossRefGoogle Scholar
  9. 9.
    Thorpe, S.J.: How can the human visual system process a natural scene in under 150ms? experiments and neural network models. In: ESANN (1997)Google Scholar
  10. 10.
    Wysoski, S.G.: Evolving Spiking Neural Networks for Adaptive Audiovisual Pattern Recognition. PhD thesis, Auckland University of Technology (August 2008), http://hdl.handle.net/10292/390
  11. 11.
    Defoin-Platel, M., Schliebs, S., Kasabov, N.: A versatile quantum-inspired evolutionary algorithm. In: IEEE Congress on Evolutionary Computation, CEC 2007, pp. 423–430 (2007)Google Scholar
  12. 12.
    Defoin-Platel, M., Schliebs, S., Kasabov, N.: Quantum-inspired evolutionary algorithm: A multimodel eda. IEEE Transactions on Evolutionary Computation (in print, 2009)Google Scholar
  13. 13.
    Valko, M., Marques, N.C., Castelani, M.: Evolutionary feature selection for spiking neural network pattern classifiers. In: Bento, et al. (eds.) Proceedings of 2005 Portuguese Conference on Artificial Intelligence, pp. 24–32. IEEE, Los Alamitos (2005)Google Scholar
  14. 14.
    Lang, K.J., Witbrock, M.J.: Learning to tell two spirals apart. In: Proceedings of the 1988 Connectionist Models Summer School San Mateo, pp. 52–59. Morgan Kauffmann, San Francisco (1988)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Stefan Schliebs
    • 1
  • Michaël Defoin-Platel
    • 2
  • Nikola Kasabov
    • 1
  1. 1.Knowledge Engineering and Discovery Research InstituteAuckland University of TechnologyNew Zealand
  2. 2.Department of Computer ScienceUniversity of AucklandNew Zealand

Personalised recommendations