Boosting and Other Machine Learning Algorithms

Harris Drucker, Corinna Cortes, Lawrence D. Jackel, Yann LeCun, Vladimir VapnikICML 1994 · OpenReview

Abstract

In an optical character recognition problem, we compare (as a function of training set size) the performance of three neural network based ensemble methods (two versions of boosting and a committee of neural networks trained independently) to that of a single network. In boosting, the number of patterns actually used for training is a subset of all potential training patterns. Based on either a fixed computational cost or training set size criterion, some version of boosting is best We also compare (for a fixed training set size) boosting to the following algorithms: optimal margin classifiers, tangent distance, local learning, k-nearest neighbor, and a large weight sharing network with the boosting algorithm showing the best performance.
BibTeX
@inproceedings{drucker1994boosting,
  author = {Harris Drucker and Corinna Cortes and Lawrence D. Jackel and Yann LeCun and Vladimir Vapnik},
  title = {{Boosting and Other Machine Learning Algorithms}},
  booktitle = {International Conference on Machine Learning},
  year = {1994},
  url = {https://openreview.net/forum?id=By-ZgsZ_Zr},
}

Loading related content...

Figure