Estimation of Input Ranking Using Input Sensitivity Approach

  • Sanggil Kang
  • Steve Morphet
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3980)


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.


Neural Network Hide Neuron Input Neuron Joint Probability Density Function Trained Neural Network 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 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)CrossRefGoogle Scholar
  2. 2.
    Tchaban, T., Taylor, M.J.: Establishing Impacts of the Inputs in a Feed-forward Neural Network. Neural Comput & Applic 7, 309–317 (1998)MATHCrossRefGoogle Scholar
  3. 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. 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)MATHCrossRefMathSciNetGoogle Scholar
  5. 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. 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)CrossRefGoogle Scholar
  7. 7.
    Piche, S.: Robustness of Feedforward Neural Networks. International Joint Conference on Neural Networks 2, 346–351 (1992)Google Scholar
  8. 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. 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

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Sanggil Kang
    • 1
  • Steve Morphet
    • 2
  1. 1.Department of Computer, College of Information EngineeringThe University of SuwonSuwon, Gyeonggi-doKorea
  2. 2.Syracuse Research CorporationSyracuseU.S.A.

Personalised recommendations