A Novel Constructive Neural Network Architecture Based on Improved Adaptive Learning Strategy for Pattern Classification

Conference paper
Part of the Advances in Intelligent and Soft Computing book series (AINSC, volume 130)

Abstract

Constructive neural network algorithms provide optimal ways to determine the architecture of a multi layer perceptron network along with learning algorithms for determining appropriate weights for pattern classification problems. In this paper the possibility of developing a novel Constructive Neural Network architecture with improved adaptive learning strategy is proposed and analyzed. The new Multi category Tiling Constructive Neural Network architecture and the existing Tiling architecture are tested on machine learning datasets. The performance of the new learning strategy on Multi Category Tiling architecture was found to be comparatively better than when applied on the existing Tiling architecture.

Keywords

Constructive Neural Networks Adaptive Learning Multi-Category Tiling architecture Pattern Classification 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Haykin, S.: Neural Networks- A Comprehensive foundation. Pearson Education (2001)Google Scholar
  2. 2.
    Bishop, C.A.: Neural Networks for Pattern Recognition. Oxford University Press (1995)Google Scholar
  3. 3.
    Gomez, I., Franco, L., Jerez, J.M.: Neural Network architecture selection: can function complexity help? Kluwer Academy publishers (2009)Google Scholar
  4. 4.
    Reed, R.: Pruning Algorithms – A survey. IEEE Transaction on Neural Networks 4(5) (1993)Google Scholar
  5. 5.
    Thimm, G., Fiesler, E.: Pruning of Neural Networks, IDIAP Research Report (1997)Google Scholar
  6. 6.
    Ash, T.: Dynamic node creation in back propagation networks. Connection Science 1, 365–375 (1989)CrossRefGoogle Scholar
  7. 7.
    Mezard, M., Nadal, J.P.: Learning in feed forward layered networks: the tiling algorithm. J. Phys. A: Math. Gen. 22, 2191–2203 (1989)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Gallant, S.: Perceptron based learning algorithms. IEEE Transaction on Neural Networks 1, 179–191 (1990)CrossRefGoogle Scholar
  9. 9.
    Frean, M.: The Upstart Algorithm: A Method for Constructing and Training Feed forward Neural Networks. Neural Computation 4, 198–209 (1990)CrossRefGoogle Scholar
  10. 10.
    Parekh, R., Yang, J., Honavar, V.: MUpstart - A Constructive Neural Network Learning Algorithm for Multi-Category Pattern Classification. IEEE (1997)Google Scholar
  11. 11.
    Fahlman, S., Leniere, C.: The Cascade correlation learning algorithm. In: Touretzhy (ed.) Information Systems. Margan-kauffman, Sanmateo (1990)Google Scholar
  12. 12.
    Marchand, M., et al.: A Convergence Theorem for Sequential Learning in Two-Layer Perceptrons. Europhys. Lett. 11, 487–492 (1990)CrossRefGoogle Scholar
  13. 13.
    Burgess, N.: Constructive Algorithm that converges for Real-valued input patterns. International Journal of Neural Systems 5(1), 59–66 (1994)CrossRefGoogle Scholar
  14. 14.
    Mascioli, F., Martinelli, G.: A constructive algorithm for binary neural networks: The Oil-Spot algorithm. IEEE Transactions on Neural Networks 6, 794–797 (1995)CrossRefGoogle Scholar
  15. 15.
    Yang, J., Parekh, R., Honavar, V.: DistAl: An inter-pattern distance Based constructive learning algorithm. Intelligent Data Analysis 3, 53–73 (1999)CrossRefGoogle Scholar
  16. 16.
    Franco, L., et al.: Early Breast cancer Prognosis prediction and Rule extraction using a New Constructive Neural Network algorithm. Springer, Heidelberg (2006)Google Scholar
  17. 17.
    Franco, L., et al.: Extension of Generalization complexity measure to real valued input datasets. Springer, Heidelberg (2010)Google Scholar
  18. 18.
    Frean, M.: A Thermal Perceptron learning rule. Neural Computation, 946–957 (1992)Google Scholar
  19. 19.
    Poulard, H., Labreche, S.: A new threshold learning algorithm, Technical report 95504, LAAS (December 1995)Google Scholar
  20. 20.
    Bertini, J.R., et al.: A Comparative Evaluation of Constructive Neural Networks Methods using PRM and BCP as TLU Training algorithms. In: IEEE International Conference on Systems, Man, and Cybernetics, Taipei, Taiwan (2006)Google Scholar
  21. 21.
    Parekh, R., Yang, J., Honavar, V.: Constructive Neural-Network learning algorithms for multicategory real-valued pattern classification, Dept. Computer. Science, Iowa State Univ., Tech. Rep. ISU-CS- TR97-06 (1997). Google Scholar
  22. 22.
    Parekh, R., Yang, J., Honovar, V.: Constructive Neural Network Learning Algorithms for Pattern Classification. IEEE Transactions on Neural Networks 11(2), 436–451, (2000)Google Scholar
  23. 23.
    Islam, M., et al.: A New Constructive algorithm for Architectural and Functional adaptation of Artificial Neural Networks. IEEE Transactions on Systems, Man and Cybernatics 39(6), 1590–1605 (2009)CrossRefGoogle Scholar
  24. 24.
    Micheli, A.: Neural Networks for Graphs: A contexual constructive approach. IEEE Transactions on Neural Networks 20(3) (2009)Google Scholar
  25. 25.
    Perambur, N.S.: Information-Theoretic Aspects of Neural Networks. CRC Press (1999)Google Scholar
  26. 26.
    Murphy, P., Aha, D.: Repository of machine learning databases. Dept. Inform. Comput. Sci., Univ., California, Irvine (1994), http://www.ics.uci.edu/AI/ML/MLDBRepository.html Google Scholar

Copyright information

© Springer India Pvt. Ltd. 2012

Authors and Affiliations

  1. 1.School of ComputingSRM UniversityChennaiIndia
  2. 2.SRM UniversityChennaiIndia

Personalised recommendations