| 基于函数集信息量的模型选择研究 |
| |
| 引用本文： | 盛守照,王道波,王志胜,黄向华.基于函数集信息量的模型选择研究[J].电子与信息学报,2005,27(4):552-555. |
| |
| 作者姓名： | 盛守照 王道波 王志胜 黄向华 |
| |
| 作者单位： | 南京航空航天大学自动化学院,南京,210016;南京航空航天大学自动化学院,南京,210016;南京航空航天大学自动化学院,南京,210016;南京航空航天大学自动化学院,南京,210016 |
| |
| 摘 要： | 提出了子空间信息量(SIQ)和函数集信息量(FSIQ)概念，详细讨论了基于函数集信息量的模型选择问题，给出了有限含噪声样本下模型选择的近似解决方法，很好地克服了模型选择过程中普遍存在的欠学习和过学习问题，大大提高了预测模型的泛化性能，在此基础上提出了一种可行的次优模型选择算法。最后通过具体实例验证了上述方法的可行性和优越性。
|
| 关 键 词： | 子空间信息量 函数集信息量 模型选择 统计学习理论 |
| 文章编号： | 1009-5896(2005)04-0552-04 |
| 收稿时间： | 2003-12-9 |
| 修稿时间： | 2003年12月9日 |
Research on Model Selection Based on Function Set Information Quantity |
| |
| SHENG Shou-zhao,WANG Dao-bo,WANG Zhi-sheng,HUANG Xiang-hua.Research on Model Selection Based on Function Set Information Quantity[J].Journal of Electronics & Information Technology,2005,27(4):552-555. |
| |
| Authors: | SHENG Shou-zhao WANG Dao-bo WANG Zhi-sheng HUANG Xiang-hua |
| |
| Affiliation: | College of Automation Engineering Nanjing University of Aeronautics and Astronautics Nanjing 210016 China |
| |
| Abstract: | The concepts of the Subspace Information Quantity(SIQ) and Function Set Information Quantity(FSIQ) are presented; Then the problem of model selection based on FSIQ are discussed explicitly, and the approximate method of model selection based on limited samples with white noise is proposed, which resolves the problem of underfilling and overfitting of mode! selection and improves the generalization of predict model well. A new suboptimal algorithm for model selection is given, and its reliability and advantage are illustrated through concrete test. |
| |
| Keywords: | Subspace Information Quantity(SIQ) Function Set Information Quantity(FSIQ) Model selection Statistical learning theory |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《电子与信息学报》浏览原始摘要信息 |
|
点击此处可从《电子与信息学报》下载全文 |
