A Smoothed Boosting Algorithm Using Probabilistic Output Codes

DMCA

A Smoothed Boosting Algorithm Using Probabilistic Output Codes (2005)

Cached

Download Links

Other Repositories/Bibliography

DBLP

by Rong Jin , Jian Zhang

Venue:	Proc. 22 nd International Conference on Machine Learning
Citations:	2 - 0 self

BibTeX

@INPROCEEDINGS{Jin05asmoothed,
    author = {Rong Jin and Jian Zhang},
    title = {A Smoothed Boosting Algorithm Using Probabilistic Output Codes},
    booktitle = {Proc. 22 nd International Conference on Machine Learning},
    year = {2005},
    pages = {361--368}
}

OpenURL

Abstract

AdaBoost.OC has shown to be an effective method in boosting “weak ” binary classifiers for multi-class learning. It employs the Error Correcting Output Code (ECOC) method to convert a multi-class learning problem into a set of binary classification problems, and applies the AdaBoost algorithm to solve them efficiently. In this paper, we propose a new boosting algorithm that improves the AdaBoost.OC algorithm in two aspects: 1) It introduces a smoothing mechanism into the boosting algorithm to alleviate the potential overfitting problem with the AdaBoost algorithm, and 2) It introduces a probabilistic coding scheme to generate binary codes for multiple classes such that training errors can be efficiently reduced. Empirical studies with seven UCI datasets have indicated that the proposed boosting algorithm is more robust and effective than the AdaBoost.OC algorithm for multi-class learning. 1.

Keyphrases

oc algorithm multi-class learning adaboost algorithm multiple class binary code potential overfitting problem multi-class learning problem boosting algorithm binary classification problem weak binary classifier error correcting output code probabilistic coding scheme new boosting algorithm empirical study effective method uci datasets smoothing mechanism

DMCA