| 有限样本下模型选择理论与方法研究 |
| |
| 引用本文： | 盛守照,王道波,黄向华. 有限样本下模型选择理论与方法研究[J]. 系统工程与电子技术, 2005, 27(4): 730-733 |
| |
| 作者姓名： | 盛守照 王道波 黄向华 |
| |
| 作者单位： | 南京航空航天大学自动化学院,江苏,南京,210016 |
| |
| 基金项目： | 航空基金项目资助课题 (0 1C5 2 0 15 ) |
| |
| 摘 要： | 从理论上给出有限样本下模型选择的方法,详细讨论了样本噪声对模型选择的影响,提出了一种次优模型选择算法,并进一步给出了一种推挽式模型选择算法,它能够有效地提高模型选择的学习速度。两种算法具有很强的抗噪声能力,预测模型也具有很好的推广性。最后通过具体数值试验验证了上述理论和方法的可行性和优越性。
|
| 关 键 词： | 模型选择 算法 统计学习理论 机器学习 |
| 文章编号： | 1001-506X(2005)04-0730-04 |
| 修稿时间： | 2004-03-31 |
Theory and method of model selection under limited samples |
| |
| SHENG Shou-zhao,WANG Dao-bo,HUANG Xiang-hua. Theory and method of model selection under limited samples[J]. System Engineering and Electronics, 2005, 27(4): 730-733 |
| |
| Authors: | SHENG Shou-zhao WANG Dao-bo HUANG Xiang-hua |
| |
| Abstract: | The method of model selection with limited samples is given in theory, and the noise's effect on the model selection is discussed. A suboptimal algorithm for model selection is proposed, then a push-pull algorithm for model selection is further presented, which can improve the learning speed of model selection effectively. The two algorithms have excellent anti-noise performance, and the prediction model has strong ability of generalization. The reliability and advantage of the above theory and method are illustrated through tests. |
| |
| Keywords: | model selection algorithm statistical learning theory machine learning |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
