Advertisement

Training Randomly Connected, Recurrent Artificial Neural Networks Using PSO

  • Vytautas Jancauskas
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6234)

Abstract

The basic particle swarm algorithm was described by Kennedy and Eberhart [4]. In this paper a modified method with time varying inertia coefficient [3] was used where the inertia coefficient w goes linearly from w start to w end .

References

  1. 1.
  2. 2.
  3. 3.
    Eberhart, R.C., Shi, Y.: Parameter selection in particle swarm optimization. In: Porto, V.W., Waagen, D. (eds.) EP 1998. LNCS, vol. 1447, pp. 591–600. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  4. 4.
    Kennedy, J., Eberhart, R.C.: Particle swarm optimization. In: Proceedings of IEEE International Conference on Neural Networks, pp. 1942–1948 (1995)Google Scholar
  5. 5.
    Meissner, M., Schmuker, M., Schneider, G.: Optimized particle swarm optimization (opso) and its application to artificial neural network training. BMC Bioinformatics 7, 125 (2006)CrossRefGoogle Scholar
  6. 6.
    Fisher, R.A.: Iris data set, http://archive.ics.uci.edu/ml/datasets/Iris

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Vytautas Jancauskas
    • 1
  1. 1.Department of Computer Science, Faculty of Mathematics and InformaticsVilnius UniversityVilniusLithuania

Personalised recommendations