The NeuralBAG algorithm: optimizing generalization performance in bagged neural networks

@inproceedings{Carney1999TheNA,
  title={The NeuralBAG algorithm: optimizing generalization performance in bagged neural networks},
  author={John Carney and Padraig Cunningham},
  booktitle={ESANN},
  year={1999}
}
In this paper we propose an algorithm we call \NeuralBAG" that estimates the set of weights and number of hidden units each network in a bagged ensemble should have so that the generalization performance of the ensemble is optimized. Experiments performed on noisy synthetic data demonstrate the potential of the algorithm. On average, ensembles trained using NeuralBAG out-perform bagged networks trained using cross-validation by 53% and individual networks trained using \cheating" 

From This Paper

Figures, tables, and topics from this paper.

Citations

Publications citing this paper.
Showing 1-10 of 25 extracted citations

References

Publications referenced by this paper.
Showing 1-6 of 6 references

Technical Report TCD-CS-1998-23

  • J. Carney, P. Cunningham
  • Computer Science Department, University of Dublin…
  • 1998
1 Excerpt

Out-of-bag estimation

  • L. Breman
  • Technical Report, Statistics Department…
  • 1996
3 Excerpts

An Introduction to the Bootstrap

  • B. Efron, R. Tibshirani
  • Chapman & Hall, London
  • 1993
1 Excerpt

Similar Papers

Loading similar papers…