| Adaboost.M1 性能提升分析 |
| |
| 引用本文： | 苏巧平,刘原,卢参义. Adaboost.M1 性能提升分析[J]. 新乡学院学报(自然科学版), 2012, 0(5): 416-420 |
| |
| 作者姓名： | 苏巧平 刘原 卢参义 |
| |
| 作者单位： | 安徽新华学院电子通信工程学院;安徽医学高等专科学校医学技术系;中国科学技术大学自动化系 |
| |
| 摘 要： | 在理论上探讨了在一个更弱的条件下 AdaBoost.M1 性能继续增强的可能性,并给出了一个更紧的误差界. 实验结果表明,在这个更弱的条件下,算法有着更强的增强能力.
|
| 关 键 词： | AdaBoost M1 算法 多类分类 集成学习 |
Analysis of Adaboost.M1 Performance Improvement |
| |
| SU Qiao-ping,LIU Yuan,LU Can-yi. Analysis of Adaboost.M1 Performance Improvement[J]. , 2012, 0(5): 416-420 |
| |
| Authors: | SU Qiao-ping LIU Yuan LU Can-yi |
| |
| Affiliation: | 1.Electronics and Communications Engineering College,Anhui Xinhua University,Hefei 230088,China; 2.Department of Medical Technology,Department of Anhui Medical College,Hefei 230000,China; 3.Department of Automation,University of Science and Technology of China,Hefei 230027,China) |
| |
| Abstract: | In this paper, the possibility is discussed that AdaBoost.M1 continues to improve the performance with a weaker condition, and a tighter error bound is also given out here. The experiment indicates that the algorithm has much better performance under the weaker condition. |
| |
| Keywords: | AdaBoost.M1 algorithm multi-class classification ensemble learning |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
