Extracting the relevant delays in time series modelling

  title={Extracting the relevant delays in time series modelling},
  author={Cyril Goutte},
In this contribution, we suggest a convenient way to use generalisation error to extract the relevant delays from a timevarying process, i.e. the delays that lead to the best prediction performance. We design a generalisation-based algorithm that takes its inspiration from traditional variable selection, and more precisely stepwise forward selection. The method is compared to other forward selection schemes, as well as to a non-parametric tests aimed at estimating the embedding dimension of… CONTINUE READING

From This Paper

Topics from this paper.


Publications referenced by this paper.
Showing 1-10 of 13 references

Comparison of two convolution models for fMRI time series

  • C. Peterson
  • 1997

Geometrical techniques for finding the embedding dimension of time series,

  • C. Molina, N. Sampson, W. J. Fitzgerald, M. Niranjan
  • Neural Networks for Signal Processing VI…
  • 1996

Note on generalization, regularization and architecture selection in nonlinear learning systems,

  • J . Moody
  • Proceedings of the first IEEE Workshop on Neural…
  • 1991

Time series and dependent variables,

  • R. Savit, M. Green
  • Physica D,
  • 1991

Similar Papers

Loading similar papers…