A Very Fast Learning Method for Neural Networks Based on Sensitivity Analysis

@article{Castillo2006AVF,
  title={A Very Fast Learning Method for Neural Networks Based on Sensitivity Analysis},
  author={Enrique F. Castillo and Bertha Guijarro-Berdi{\~n}as and Oscar Fontenla-Romero and Amparo Alonso-Betanzos},
  journal={Journal of Machine Learning Research},
  year={2006},
  volume={7},
  pages={1159-1182}
}
This paper introduces a learning method for two-layer feedforward neural networks based on sensitivity analysis, which uses a linear training algorithm for each of the two layers. First, random values are assigned to the outputs of the first layer; later, these initial values are updated based on sensitivity formulas, which use the weights in each of the layers; the process is repeated until convergence. Since these weights are learnt solving a linear system of equations, there is an important… CONTINUE READING
Highly Cited
This paper has 387 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 49 extracted citations

387 Citations

050100'08'11'14'17
Citations per Year
Semantic Scholar estimates that this publication has 387 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 51 references

A perturbation approach to sensitivity analysis in nonlinear programming

  • E. Castillo, C. Castillo A. Conejo, R. Mı́nguez, D. Ortigosa
  • Journal of Optimization Theory and Applications,
  • 2006
1 Excerpt

Similar Papers

Loading similar papers…