Advertisement

Soft Patterns Reduction for RBF Network Performance Improvement

  • Pawel RozyckiEmail author
  • Janusz Kolbusz
  • Oleksandr Lysenko
  • Bogdan M. Wilamowski
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10841)

Abstract

Successful training of artificial neural networks depends primarily on used architecture and suitable algorithm that is able to train given network. During training process error for many patterns reach low level very fast while for other patterns remains on relative high level. In this case already trained patterns make impossible to adjust all trainable network parameters and overall training error is unable to achieve desired level. The paper proposes soft pattern reduction mechanism that allows to reduce impact of already trained patterns which helps in getting better results for all training patterns. Suggested approach has been confirmed by several experiments.

Keywords

RBF network training improvement ErrCor Error Correction Soft patterns reduction 

References

  1. 1.
    Wilamowski, B.M., Yu, H.: Neural network learning without backpropagation. IEEE Trans. Neural Netw. 21(11), 1793–1803 (2010)CrossRefGoogle Scholar
  2. 2.
    Wilamowski, B.M.: Neural network architectures and learning algorithms, how not to be frustrated with neural networks. IEEE Ind. Electron. Mag. 3(4), 56–63 (2009)CrossRefGoogle Scholar
  3. 3.
    Hunter, D., Yu, H., Pukish, M.S., Kolbusz, J., Wilamowski, B.M.: Selection of proper neural network sizes and architectures-a comparative study. IEEE Trans. Ind. Inf. 8, 228–240 (2012)CrossRefGoogle Scholar
  4. 4.
    Hohil, M.E., Liu, D.: Solving the N-bit parity problem using neural networks. Neural Netw. 12, 1321–1323 (1999)CrossRefGoogle Scholar
  5. 5.
    Wilamowski, B.M.: Challenges in applications of computational intelligence in industrial electronics. In: ISIE 2010, pp. 15–22, 4–7 July 2010Google Scholar
  6. 6.
    Fahlman, S.E., Lebiere, C.: The cascade-correlation learning architecture. In: Advances in Neural Information Processing Systems 2, pp. 524–532. Morgan Kaufmann, San Mateo (1990)Google Scholar
  7. 7.
    Lang, K.L., Witbrock, M.J.: Learning to tell two spirals apart. In: Proceedings of the 1988 Connectionists Models Summer School. Morgan Kaufman (1998)Google Scholar
  8. 8.
    Wilamowski, B.M., Korniak, J.: Learning architectures with enhanced capabilities and easier training. In: 19th IEEE International Conference on Intelligent Engineering Systems (INES 2015), 03–05 September, pp. 21–29 (2015)Google Scholar
  9. 9.
    Nguyen, G.H., Bouzerdoum, A., Phung, S.L.: Efficient supervised learning with reduced training exemplars. In: 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), Hong Kong, pp. 2981–2987 (2008)Google Scholar
  10. 10.
    Lozano, M.T.: Data reduction techniques in classification processes. Ph.D. Dissertation, Universitat Jaume I, Spain (2007)Google Scholar
  11. 11.
    Chouvatut, V., Jindaluang, W., Boonchieng, E.: Training set size reduction in large dataset problems. In: 2015 International Computer Science and Engineering Conference (ICSEC), Chiang Mai, pp. 1–5 (2015)Google Scholar
  12. 12.
    Kolbusz, J., Rozycki, P.: Outliers elimination for error correction algorithm improvement. In: CS&P Proceedings 24th International Workshop Concurrency, Specification & Programming, (CS&P 2015), vol. 2, pp. 120–129 (2015)Google Scholar
  13. 13.
    Rozycki, P., Kolbusz, J., Lysenko, O., Wilamowski, B.M.: Neural network training improvement by patterns removing. Artif. Intell. Soft Comput. ICAISC 2017, 154–164 (2017)Google Scholar
  14. 14.
    Yu, H., Reiner, P., Xie, T., Bartczak, T., Wilamowski, B.M.: An incremental design of radial basis function networks. IEEE Trans. Neural Netw. Learn. Syst. 25(10), 1793–1803 (2014)CrossRefGoogle Scholar
  15. 15.
    Xie, T.: Growing and learning algorithms of radial basis function networks. Ph.D. Dissertation, Auburn University, USA (2013)Google Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  • Pawel Rozycki
    • 1
    Email author
  • Janusz Kolbusz
    • 1
  • Oleksandr Lysenko
    • 2
  • Bogdan M. Wilamowski
    • 3
  1. 1.University of Information Technology and Management in RzeszowRzeszowPoland
  2. 2.National Technical University of Ukraine “Igor Sikorsky Kyiv Polytechnic Institute”KyivUkraine
  3. 3.Auburn UniversityAuburnUSA

Personalised recommendations