Generalization ability of fractional polynomial models
文献类型：期刊论文
| 作者 | Lei, Yunwen1; Ding, Lixin1; Ding, Yiming2 |
| 刊名 | NEURAL NETWORKS
 |
| 出版日期 | 2014 |
| 卷号 | 49页码:59-73 |
| 关键词 | Learning algorithm Learning theory Fractional polynomial Model selection Approximation theory |
| 英文摘要 | In this paper, the problem of learning the functional dependency between input and output variables from scattered data using fractional polynomial models (FPM) is investigated. The estimation error bounds are obtained by calculating the pseudo-dimension of FPM, which is shown to be equal to that of sparse polynomial models (SPM). A linear decay of the approximation error is obtained for a class of target functions which are dense in the space of continuous functions. We derive a structural risk analogous to the Schwartz Criterion and demonstrate theoretically that the model minimizing this structural risk can achieve a favorable balance between estimation and approximation errors. An empirical model selection comparison is also performed to justify the usage of this structural risk in selecting the optimal complexity index from the data. We show that the construction of FPM can be efficiently addressed by the variable projection method. Furthermore, our empirical study implies that FPM could attain better generalization performance when compared with SPM and cubic splines. (C) 2013 Elsevier Ltd. All rights reserved. |
| WOS标题词 | Science & Technology ; Technology ; Life Sciences & Biomedicine |
| 类目[WOS] | Computer Science, Artificial Intelligence ; Neurosciences |
| 研究领域[WOS] | Computer Science ; Neurosciences & Neurology |
| 关键词[WOS] | NONLINEAR LEAST-SQUARES ; COVERING NUMBER ; NEURAL-NETWORKS ; VC-DIMENSION ; REGRESSION ; BOUNDS ; CLASSIFICATION ; APPROXIMATION ; SELECTION ; COMPLEXITY |
| 收录类别 | SCI |
| 语种 | 英语 |
| WOS记录号 | WOS:000331130000008 |
| 公开日期 | 2015-07-14 |
| 源URL | [http://ir.wipm.ac.cn/handle/112942/1329]  |
| 专题 | 武汉物理与数学研究所_数学物理与应用研究部 |
| 作者单位 | 1.Wuhan Univ, Sch Comp, State Key Lab Software Engn, Wuhan 430072, Peoples R China 2.Chinese Acad Sci, Wuhan Inst Phys & Math, Wuhan 430071, Peoples R China |
| 推荐引用方式 GB/T 7714 | Lei, Yunwen,Ding, Lixin,Ding, Yiming. Generalization ability of fractional polynomial models[J]. NEURAL NETWORKS,2014,49:59-73. |
| APA | Lei, Yunwen,Ding, Lixin,&Ding, Yiming.(2014).Generalization ability of fractional polynomial models.NEURAL NETWORKS,49,59-73. |
| MLA | Lei, Yunwen,et al."Generalization ability of fractional polynomial models".NEURAL NETWORKS 49(2014):59-73. |
入库方式： OAI收割
来源：武汉物理与数学研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。