Explaining adaboost

Robert E. Schapire

doi:10.1007/978-3-642-41136-6_5

Explaining adaboost

Robert E. Schapire

Research output: Chapter in Book/Report/Conference proceeding › Chapter

891 Scopus citations

Abstract

Boosting is an approach to machine learning based on the idea of creating a highly accurate prediction rule by combining many relatively weak and inaccurate rules. The AdaBoost algorithm of Freund and Schapire was the first practical boosting algorithm, and remains one of the most widely used and studied, with applications in numerous fields. This chapter aims to review some of the many perspectives and analyses of AdaBoost that have been applied to explain or understand it as a learning method, with comparisons of both the strengths and weaknesses of the various approaches.

Original language	English (US)
Title of host publication	Empirical Inference
Subtitle of host publication	Festschrift in Honor of Vladimir N. Vapnik
Publisher	Springer Berlin Heidelberg
Pages	37-52
Number of pages	16
ISBN (Electronic)	9783642411366
ISBN (Print)	9783642411359
DOIs	https://doi.org/10.1007/978-3-642-41136-6_5
State	Published - Jan 1 2013
Externally published	Yes

All Science Journal Classification (ASJC) codes

General Computer Science

Access to Document

10.1007/978-3-642-41136-6_5

Cite this

@inbook{77a4e30339354a639e306fbbf82632f5,

title = "Explaining adaboost",

abstract = "Boosting is an approach to machine learning based on the idea of creating a highly accurate prediction rule by combining many relatively weak and inaccurate rules. The AdaBoost algorithm of Freund and Schapire was the first practical boosting algorithm, and remains one of the most widely used and studied, with applications in numerous fields. This chapter aims to review some of the many perspectives and analyses of AdaBoost that have been applied to explain or understand it as a learning method, with comparisons of both the strengths and weaknesses of the various approaches.",

author = "Schapire, {Robert E.}",

note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2013.",

year = "2013",

month = jan,

day = "1",

doi = "10.1007/978-3-642-41136-6_5",

language = "English (US)",

isbn = "9783642411359",

pages = "37--52",

booktitle = "Empirical Inference",

publisher = "Springer Berlin Heidelberg",

}

TY - CHAP

T1 - Explaining adaboost

AU - Schapire, Robert E.

N1 - Publisher Copyright: © Springer-Verlag Berlin Heidelberg 2013.

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Boosting is an approach to machine learning based on the idea of creating a highly accurate prediction rule by combining many relatively weak and inaccurate rules. The AdaBoost algorithm of Freund and Schapire was the first practical boosting algorithm, and remains one of the most widely used and studied, with applications in numerous fields. This chapter aims to review some of the many perspectives and analyses of AdaBoost that have been applied to explain or understand it as a learning method, with comparisons of both the strengths and weaknesses of the various approaches.

AB - Boosting is an approach to machine learning based on the idea of creating a highly accurate prediction rule by combining many relatively weak and inaccurate rules. The AdaBoost algorithm of Freund and Schapire was the first practical boosting algorithm, and remains one of the most widely used and studied, with applications in numerous fields. This chapter aims to review some of the many perspectives and analyses of AdaBoost that have been applied to explain or understand it as a learning method, with comparisons of both the strengths and weaknesses of the various approaches.

UR - http://www.scopus.com/inward/record.url?scp=84931574142&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84931574142&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-41136-6_5

DO - 10.1007/978-3-642-41136-6_5

M3 - Chapter

AN - SCOPUS:84931574142

SN - 9783642411359

SP - 37

EP - 52

BT - Empirical Inference

PB - Springer Berlin Heidelberg

ER -

Explaining adaboost

Abstract

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this