Experiments with a New Boosting Algorithm
@inproceedings{Freund1996ExperimentsWA, title={Experiments with a New Boosting Algorithm}, author={Y. Freund and R. Schapire}, booktitle={ICML}, year={1996} }
In an earlier paper, we introduced a new "boosting" algorithm called AdaBoost which, theoretically, can be used to significantly reduce the error of any learning algorithm that con- sistently generates classifiers whose performance is a little better than random guessing. [...] Key Result In the second set of experiments, we studied in more detail the performance of boosting using a nearest-neighbor classifier on an OCR problem.Expand Abstract
7,968 Citations
Improved Boosting Algorithms using Confidence-Rated Predictions
- Mathematics, Computer Science
- COLT
- 1998
- 2,060
- PDF
Stopping Criterion for Boosting-Based Data Reduction Techniques: from Binary to Multiclass Problem
- Mathematics, Computer Science
- J. Mach. Learn. Res.
- 2002
- 37
- PDF
Supervised projection approach for boosting classifiers
- Mathematics, Computer Science
- Pattern Recognit.
- 2009
- 20
- Highly Influenced
- PDF
An Empirical Boosting Scheme for ROC-Based Genetic Programming Classifiers
- Computer Science
- EuroGP
- 2007
Training Methods for Adaptive Boosting of Neural Networks
- Computer Science
- NIPS
- 1997
- 61
- Highly Influenced
- PDF
References
SHOWING 1-10 OF 35 REFERENCES
A decision-theoretic generalization of on-line learning and an application to boosting
- Computer Science
- EuroCOLT
- 1995
- 11,982
- PDF
A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting
- Computer Science, Mathematics
- J. Comput. Syst. Sci.
- 1997
- 6,407
- PDF
On the boosting ability of top-down decision tree learning algorithms
- Mathematics, Computer Science
- STOC '96
- 1996
- 128
- PDF
Boosting Performance in Neural Networks
- Computer Science
- Int. J. Pattern Recognit. Artif. Intell.
- 1993
- 230