摘要
Boosting是一种改善任意给定的机器学习算法准确性的通用方法 .主要针对 Ada Boost算法 ,介绍了 Ad-a Boost算法的研究背景 .分析了实验过程中出现的退化问题以及目标类权重分布扭曲的现象 ,提出了一种基于调整权重分布 ,限制权重扩张的改进方法 。
Boosting is a general method for improving the accuracy of any given learning algorithm. Focusing primarily on the AdaBoost algorithm, the former part overviews the research background of AdaBoost. In the latter part, we introduce a problem of degradation occurring in the experiments and come up with a weight adjusting based method to improve AdaBoost, and also provide the analyses of its experiment results.
出处
《小型微型计算机系统》
CSCD
北大核心
2004年第5期869-871,共3页
Journal of Chinese Computer Systems