Synonyms
Definition
AdaBoost is an algorithm that builds a classifier by combining additively a set of weak classifiers. The weak classifiers are incorporated sequentially one at a time so that their combination reduces the empirical exponential loss.
Background
Boosting is a procedure to combine several classifiers with weak performance into one with arbitrarily high performance [1, 2] and was originally introduced by Robert Schapire in the machine learning community [3]. AdaBoost is a popular implementation of boosting for binary classification [4]. The enthusiasm generated by boosting, and in particular by AdaBoost, in machine learning can be highlighted via a quote of Breiman [1] saying that AdaBoost with trees is the “best off-the-shelf classifier in the world.” In practice, much of the popularity of AdaBoost is due to both its performance being in the same league as support vector machines [5] and its algorithmic simplicity. In the computer...
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Friedman JH, Hastie T, Tibshirani R (2000) Additive logistic regression: a statistical view of boosting. Ann Stat 28(2): 337–374
Hastie T, Tibshirani R, Friedman J (2001) The elements of statistical learning. Springer, New York
Schapire RE (1990) The strength of weak learnability. Mach Learn 5(2):197–227
Freund Y, Schapire RE (1996) Experiments with a new boosting algorithm. In: Proceedings of the 13th international conference on machine learning, Bari, 148–156
Vapnik V (1995) The nature of statistical learning theory. Springer, New York
Viola P, Jones M (2001) Robust real-time object detection. In: Proceedings of IEEE workshop on statistical and computational theories of vision, Vancouver, Canada
Papageorgiou CP, Oren M, Poggio T (1998) A general framework for object detection. In: International conference on computer vision, Bombay, pp 555–562
Sun Y, Li J, Hager W (2004) Two new regularized adaboost algorithms. In: Machine learning and applications, Louisville, pp 41–48
Schapire RE, Singer Y (1998) Improved boosting algorithms using confidence-rated predictions. In: Computational learning theory, Springer, New York, pp 80–91
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer Science+Business Media New York
About this entry
Cite this entry
Favaro, P., Vedaldi, A. (2014). AdaBoost. In: Ikeuchi, K. (eds) Computer Vision. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-31439-6_663
Download citation
DOI: https://doi.org/10.1007/978-0-387-31439-6_663
Published:
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-30771-8
Online ISBN: 978-0-387-31439-6
eBook Packages: Computer ScienceReference Module Computer Science and Engineering