Regularization Learning and Early Stopping in Linear Networks

@inproceedings{Hagiwara2000RegularizationLA,
  title={Regularization Learning and Early Stopping in Linear Networks},
  author={Katsuyuki Hagiwara and Kazuhiro Kuno},
  booktitle={IJCNN},
  year={2000}
}
Generally, learning is performed so as to minimize the sum of squared errors between network outputs and training data. Unfortunately, this procedure does not necessarily give us a network with good generalization ability when the number of connection weights are relatively large. In such situation, overfitting to the training data occurs. To overcome this problem, there are several approaches such as regularization Iearning[6][11][12][16] and early stopping[2][15]. It has been suggested that… CONTINUE READING
Highly Cited
This paper has 29 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 17 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 15 references

Bias - variance , regularization , instability and stabilization ”

  • L. Breiman
  • 1998

Statistical theories of model fitting

  • B D.Ripley
  • In Neural Networks and Machine Learning,
  • 1998

Neural networks for pattern recognition

  • C M.Bishop
  • 1995

Similar Papers

Loading similar papers…