Cost-Sensitive Greedy Network-Growing Algorithm with Gaussian Activation Functions

  • Ryotaro Kamimura
  • Osamu Uchida
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3316)

Abstract

In this paper, we propose a new network-growing algorithm which is called the cost-sensitive greedy network-growing algorithm. This new method can maximize information while controlling the associated cost. Experimantal results show that the cost minimization approximates input patterns as much as possible, while information maximization aims to extract distinctive features.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Fahlman, S.E., Lebiere, C.: The cascade-correlation learning architecture. In: Advances in Neural Information Processing, vol. 2, pp. 524–532. Morgan Kaufmann Publishers, San Mateo (1990)Google Scholar
  2. 2.
    Shultz, T.A., Rivest, F.: Knowledge-based cascade-correlation: Using knowledge to speed learning. Connection Science 13, 43–72 (2001)MATHCrossRefGoogle Scholar
  3. 3.
    Lehtokangas, M.: Modelling with constructive backpropagation architecture. Neural Networks 12, 707–716 (1999)CrossRefGoogle Scholar
  4. 4.
    Kamimura, R., Kamimura, T., Takeuchi, H.: Greedy information acquisition algorithm: A new information theoretic approach to dynamic information acquisition in neural networks. Connection Science 14(2), 137–162 (2002)CrossRefGoogle Scholar
  5. 5.
    Kamimura, R.: Progressive feature extraction by greedy network-growing algorithm. Complex Systems 14(2), 127–153 (2003)MATHMathSciNetGoogle Scholar
  6. 6.
    Kamimura, R., Kamimura, T., Uchida, O., Takeuchi, H.: Greedy information acquisition algorithm. In: Proc. of International Joint Conference on Neural Networks (2002)Google Scholar
  7. 7.
    Kamimura, R., Uchida, O.: Accelerated Greedy Network-Growing Algorithmwith application to Student Survey. In: Proc. of IASTED International Conference on Applied Simulation and Modelling (2003)Google Scholar
  8. 8.
    Kamimura, R., Uchida, O.: Improving Feature Extraction Performance of Greedy Network-Growing Algorithm. In: Liu, J., Cheung, Y.-m., Yin, H. (eds.) IDEAL 2003. LNCS, vol. 2690, pp. 1056–1061. Springer, Heidelberg (2003)Google Scholar
  9. 9.
    Gatlin, L.L.: Information Theory and Living Systems. Columbia University Press (1972)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Ryotaro Kamimura
    • 1
  • Osamu Uchida
    • 2
  1. 1.Information Science LaboratoryTokai UniversityKanagawaJapan
  2. 2.Department of Human and Information Science, School of Information Technology and ElectronicsTokai UniversityKanagawaJapan

Personalised recommendations