Generalization by weight-elimination applied to currency exchange rate prediction

@article{Weigend1991GeneralizationBW,
  title={Generalization by weight-elimination applied to currency exchange rate prediction},
  author={A. S. Weigend and D. E. Rumelhart and B. A. Huberman},
  journal={[Proceedings] 1991 IEEE International Joint Conference on Neural Networks},
  year={1991},
  pages={2374-2379 vol.3}
}
The authors focus on the minimal network strategy. The underlying hypothesis is that if several nets fit the data equally well, the simplest one will on average provide the best generalization. Inspired by the information theoretic idea of minimum description length, a term is added to the backpropagation cost function that penalizes network complexity. The authors give the details of the procedure, called weight-elimination, describe its dynamics, and clarify the meaning of the parameters… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 81 CITATIONS, ESTIMATED 100% COVERAGE

Optimal design of neural networks for land-cover classification from multispectral imagery

Jose L. Silvan-Cardenas
  • SPIE Remote Sensing
  • 2004
VIEW 5 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

A Novel Pruning Algorithm for Smoothing Feedforward Neural Networks Based on Group Lasso Method

  • IEEE Transactions on Neural Networks and Learning Systems
  • 2018
VIEW 3 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Application of ANN in Pavement Engineering: State-of-Art

Miguel Abambres, Adelino Ferreira
  • 2019
VIEW 1 EXCERPT
CITES BACKGROUND

Sparse Artificial Neural Networks Using a Novel Smoothed LASSO Penalization

  • IEEE Transactions on Circuits and Systems II: Express Briefs
  • 2019
VIEW 1 EXCERPT

FILTER CITATIONS BY YEAR

1992
2019

CITATION STATISTICS

  • 3 Highly Influenced Citations