Computer Engineering and Applications ›› 2013, Vol. 49 ›› Issue (15): 133-135.
Previous Articles Next Articles
LIU Jianwei, FU Jie, LUO Xionglin
Online:
Published:
刘建伟,付 捷,罗雄麟
Abstract: According to weight update model via distance and lost function regularization, proposed by J.Kivinen and M.K.Warmuth, using relative entropy, Itakura-Saito, first order exponential approximation distance function, combined with relative entropy lost function, this paper devises three sorts of weight update method of weak classifier of AdaBoost. Using the UCI real datasets, the three algorithms AdaBoostRE, AdaBoostIE, AdaBoostEE are compared with three leading assembly classifier:Real AdaBoost, Gentle AdaBoost and Modest AdaBoost. Experimental results show promising performance of the proposed method.
Key words: distance function, loss function, regularization, AdaBoost algorithm
摘要: 基于距离函数和损失函数正则化的权值更新模式,使用相关熵距离函数,Itakura-Saito距离函数,指数一次近似距离和相关熵损失函数结合,实现了三种AdaBoost弱分类器权值更新算法。使用UCI数据库数据对提出的三种算法AdaBoostRE,AdaBoostIE,AdaBoostEE与Real AdaBoost,Gentle AdaBoost和Modest AdaBoost算法作了比较,可以看到提出的AdaBoostRE算法预测效果最好,优于Real AdaBoost,Gentle AdaBoost和Modest AdaBoost算法。
关键词: 距离函数, 损失函数, 正则化, AdaBoost算法
LIU Jianwei, FU Jie, LUO Xionglin. AdaBoost algorithm based on distance and loss function constraint regularization[J]. Computer Engineering and Applications, 2013, 49(15): 133-135.
刘建伟,付 捷,罗雄麟. 距离和损失函数约束正则化的AdaBoost算法[J]. 计算机工程与应用, 2013, 49(15): 133-135.
0 / Recommend
Add to citation manager EndNote|Ris|BibTeX
URL: http://cea.ceaj.org/EN/
http://cea.ceaj.org/EN/Y2013/V49/I15/133