Advertisement

Sensitivity Analysis of Madalines to Weight Perturbation

  • Yingfeng Wang
  • Xiaoqin Zeng
  • Daniel S. Yeung
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3930)

Abstract

This paper aims at exploring the behavior of the sensitivity for an ensemble of Madalines. An algorithm is first given to compute the Madalines’ sensitivity, and its efficiency is verified by computer simulations. Then, based on the algorithm, the sensitivity analysis is conducted, which shows that the dimension of input has little effect on the sensitivity as long as the dimension is sufficient large, and the increases in the number of Adalines in a layer and the number of layers will lead the sensitivity to increase under an upper bound. The analysis results will be useful for designing robust Madalines.

Keywords

Neural Network Weight Vector Input Vector Feedforward Neural Network Output Deviation 
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.
    Stevenson, M., Winter, R., Widrow, B.: Sensitivity of Feedforward Neural Networks to Weight Errors. IEEE Trans. on Neural Networks 1(1), 71–80 (1990)CrossRefGoogle Scholar
  2. 2.
    Choi, J.Y., Choi, C.H.: Sensitivity Analysis of Multilayer Perceptron with Differentiable Activation Functions. IEEE Trans. on Neural Networks 3(1), 101–107 (1992)CrossRefGoogle Scholar
  3. 3.
    Fu, L., Chen, T.: Sensitivity Analysis for Input Vector in Multilayer Feedforward Neural Networks. In: Proc. of IEEE Int. Conf. on Neural Networks, vol. 1, pp. 215–218 (1993)Google Scholar
  4. 4.
    Piché, S.W.: The Selection of Weight Accuracies for Madalines. IEEE Trans. on Neural Networks 6(2), 432–445 (1995)CrossRefGoogle Scholar
  5. 5.
    Oh, S.H., Lee, Y.: Sensitivity Analysis of a Single Hidden-Layer Neural Networks with Threshold Function. IEEE Trans. on Neural Networks 6(4), 1005–1007 (1995)CrossRefGoogle Scholar
  6. 6.
    Zeng, X., Yeung, D.S.: Sensitivity Analysis of Multilayer Perceptron to Input and Weight Perturbations. IEEE Trans. on Neural Networks 12(6), 1358–1366 (2001)CrossRefGoogle Scholar
  7. 7.
    Zeng, X., Yeung, D.S.: A Quantified Sensitivity Measure for Multilayer Perceptron to Input Perturbation. Neural Computation 15(1), 183–212 (2003)MATHCrossRefGoogle Scholar
  8. 8.
    Wang, Y., Zeng, X., Han, L.: Sensitivity of Madalines to Input and Weight Perturbations. In: Proceedings of IEEE International Conference on Machine Learning and Cybernetics, November 2003, pp. 1349–1354 (2003)Google Scholar
  9. 9.
    Gong, J., Zhao, G.: An approximate algorithm for bivariate normal integral. Computational Structural Mechanics and Applications 13(4), 494–497 (1996)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Yingfeng Wang
    • 1
  • Xiaoqin Zeng
    • 1
  • Daniel S. Yeung
    • 2
  1. 1.Department of Computer Science and EngineeringHohai UniversityNanjingChina
  2. 2.Department of computingThe Hong Kong Polytechnic UniversityKowloon, Hong Kong

Personalised recommendations