[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to main content
Springer Nature Link
Log in

Estimation of Input Ranking Using Input Sensitivity Approach

  • Conference paper
Computational Science and Its Applications - ICCSA 2006 (ICCSA 2006)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 3980))

Included in the following conference series:

  • 1226 Accesses

Abstract

In feed-forward neural networks, all inputs contribute to a greater or lesser extent when calculating the outputs. Therefore, inputs may be ordered from the greatest contributor to the least. Input ranking is non-trivial – cursory examination of the weight and bias matrices fails to reveal ranking. Solving the ranking issue allows the elimination of inputs with little influence on output. This paper presents a new method of determining the input sensitivity of three-layer feed-forward neural networks. Specifically, sensitivity of an input is independent of the magnitudes of the remaining inputs, providing an unambiguous ranking of input importance. Small changes to influential inputs will result in great changes to output. This concept motivated the theoretical approach to input ranking. Examination of theoretical results will demonstrate the correctness of this approach.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Choi, J.Y., Choi, C.H.: Sensitivity Analysis of Multilayer Perceptron with Differentiable Activation Functions. IEEE Transactions on Neural Networks 3(1), 101–107 (1992)

    Article  Google Scholar 

  2. Tchaban, T., Taylor, M.J.: Establishing Impacts of the Inputs in a Feed-forward Neural Network. Neural Comput & Applic 7, 309–317 (1998)

    Article  MATH  Google Scholar 

  3. Engelbrecht, A.P., Cloete, I., Zurada, J.M.: Determining the Significance of Input Parameters Using Sensitivity Analysis. In: Proceedings of International Workshop on Artificial Neural Networks, pp. 382–388 (1995)

    Google Scholar 

  4. Belkina, N.V., Krepets, V.V., Shakin, V.V.: One Stable Estimation of the Parameters of Feed-forward Neural Networks in Dealing with Biological Objects. Automation and Remote Control 63(1), 66–75 (2002)

    Article  MATH  MathSciNet  Google Scholar 

  5. Zurada, J.M., Malinowski, A., Cloete, I.: Sensitivity Analysis for Minimization of Input Data Dimension for Feedforward Neural Network. In: Proceedings of IEEE International Symposium on Circuits and Systems, vol. 6, pp. 447–450 (1995)

    Google Scholar 

  6. Fu, L., Chen, T.: Sensitivity Analysis for Input Vector in Multilayer Feedforward Neural Network. IEEE International Conference on Neural Networks 1, 215–218 (1993)

    Article  Google Scholar 

  7. Piche, S.: Robustness of Feedforward Neural Networks. International Joint Conference on Neural Networks 2, 346–351 (1992)

    Google Scholar 

  8. He, F., Sung, A.H., Guo, B.: ANeural Network Model for Prediction of Oil Well Cement Bonding Quality. In: Proceedings of IASTED International Conference on Control, pp. 417–420 (1997)

    Google Scholar 

  9. Sung, A.H.: Ranking Input Importance in Neural Network Modeling of Engineering Problems. In: Proceedings of IEEE International Joint Conference on Neural Networks, vol. 1, pp. 316–321 (1998)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer, College of Information Engineering, The University of Suwon, Suwon, Gyeonggi-do, Korea

    Sanggil Kang

  2. Syracuse Research Corporation, Syracuse, NY, 13212, U.S.A.

    Steve Morphet

Authors
  1. Sanggil Kang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Steve Morphet
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Computer Science, University of Calgary, 2500 University Drive N.W., T2N 1N4, Calgary, AB, Canada

    Marina Gavrilova

  2. Department of Mathematics and Computer Science, University of Perugia, via Vanvitelli, 1, I-06123, Perugia, Italy

    Osvaldo Gervasi

  3. William Norris Professor, Head of the Computer Science and Engineering Department, University of Minnesota, USA

    Vipin Kumar

  4. OptimaNumerics Ltd., Cathedral House, 23-31 Waring Street, BT1 2DX, Belfast, UK

    C. J. Kenneth Tan

  5. Clayton School of IT, Monash University, 3800, Clayton, Australia

    David Taniar

  6. Department of Chemistry, University of Perugia, Via Elce di Sotto, 8, I-06123, Perugia, Italy

    Antonio Laganá

  7. School of Computing, Soongsil University, Seoul, Korea

    Youngsong Mun

  8. School of Information and Communication Engineering, Sungkyunkwan University, Korea

    Hyunseung Choo

Rights and permissions

Reprints and permissions

Copyright information

© 2006 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Kang, S., Morphet, S. (2006). Estimation of Input Ranking Using Input Sensitivity Approach. In: Gavrilova, M., et al. Computational Science and Its Applications - ICCSA 2006. ICCSA 2006. Lecture Notes in Computer Science, vol 3980. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11751540_123

Download citation

  • DOI: https://doi.org/10.1007/11751540_123

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-34070-6

  • Online ISBN: 978-3-540-34071-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation