A node pruning algorithm based on a Fourier amplitude sensitivity test method

  title={A node pruning algorithm based on a Fourier amplitude sensitivity test method},
  author={Alfred Jean Philippe Lauret and Eric Fock and Thierry Alex Mara},
  journal={IEEE Transactions on Neural Networks},
In this paper, we propose a new pruning algorithm to obtain the optimal number of hidden units of a single layer of a fully connected neural network (NN). The technique relies on a global sensitivity analysis of model output. The relevance of the hidden nodes is determined by analysing the Fourier decomposition of the variance of the model output. Each hidden unit is assigned a ratio (the fraction of variance which the unit accounts for) that gives their ranking. This quantitative information… CONTINUE READING
Highly Cited
This paper has 110 citations. REVIEW CITATIONS
39 Citations
28 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 39 extracted citations

111 Citations

Citations per Year
Semantic Scholar estimates that this publication has 111 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 28 references

Engelbretch, “A new pruning heuristic based on var iance analysis of sensitivity information,

  • A P.
  • IEEE Transactions on Neural Networks ,
  • 2001
Highly Influential
9 Excerpts

Sensitivity Analysis

  • A. Saltelli, K.-S. Chan, E. M. Scott
  • New York: Wiley
  • 2000
Highly Influential
20 Excerpts

Neural network approach to sens itivity and uncertainty analysis,

  • M. E. Ricotti, E. Zio
  • Reliability Engineering and System Safety ,
  • 1999
Highly Influential
6 Excerpts


  • A. Saltelli
  • Tarantola, and K.-S. Chan, “A quantitat ive…
  • 1999
Highly Influential
14 Excerpts

Regularization and complexity control in f eed-forward networks,

  • C. M. Bishop
  • Neural Computing Research Group, As ton…
  • 1995
Highly Influential
6 Excerpts

Removal of hidden units and weights for bac kpropagation networks,

  • M. Hagiwara
  • inInternational Joint Conference on Neural…
  • 1993
Highly Influential
6 Excerpts

Similar Papers

Loading similar papers…