Knowledge Commons of Institute of Automation,CAS
A generalized-constraint neural network model: Associating partially known relationships for nonlinear regressions | |
Hu, Bao-Gang1,2; Qu, Han-Bing3; Wang, Yong2; Yang, Shuang-Hong4 | |
发表期刊 | INFORMATION SCIENCES |
2009-05-30 | |
卷号 | 179期号:12页码:1929-1943 |
文章类型 | Article |
摘要 | In an attempt to enhance the neural network technique so that it can evolve from a "black box" tool into a semi-analytical one, we propose a novel modeling approach of imposing "generalized constraints" on a standard neural network. We redefine approximation problems by use of a new formalization with the aim of embedding prior knowledge explicitly into the model to the maximum extent. A generalized-constraint neural network (GCNN) model has therefore been developed, which basically consists of two submodels. One is constructed by the standard neural network technique to approximate the unknown part of the target function. The other is formed from partially known relationships to impose generalized constraints on the whole model. Three issues arising after combination of the two submodels are discussed: (a) the better approximation provided by the GCNN model compared with a standard neural network, (b) the identifiability of parameters in the partially known relationships, and (c) the discrepancy in the approximation due to removable singularities in the target function. Numerical studies of three benchmark problems show important findings that have not previously been reported in the literature. Significant benefits were observed from using the GCNN model in comparison with a standard neural network. (c) 2009 Elsevier Inc. All rights reserved. |
关键词 | Nonlinear Approximation Prior Knowledge Constraints Parameter Identifiability Black Box |
WOS标题词 | Science & Technology ; Technology |
关键词[WOS] | PRIOR KNOWLEDGE ; INFORMATION ; FRAMEWORK |
收录类别 | SCI |
语种 | 英语 |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Information Systems |
WOS记录号 | WOS:000265968100011 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/2795 |
专题 | 多模态人工智能系统全国重点实验室_多媒体计算 |
作者单位 | 1.Chinese Acad Sci, Inst Automat, NLPR LIAMA, Beijing 100080, Peoples R China 2.Chinese Acad Sci, Beijing Grad Sch, Beijing 100049, Peoples R China 3.Beijing Acad Sci & Technol, Beijing Pattern Recognit Tech Res Ctr, Beijing, Peoples R China 4.Georgia Inst Technol, Coll Comp, Atlanta, GA 30332 USA |
第一作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Hu, Bao-Gang,Qu, Han-Bing,Wang, Yong,et al. A generalized-constraint neural network model: Associating partially known relationships for nonlinear regressions[J]. INFORMATION SCIENCES,2009,179(12):1929-1943. |
APA | Hu, Bao-Gang,Qu, Han-Bing,Wang, Yong,&Yang, Shuang-Hong.(2009).A generalized-constraint neural network model: Associating partially known relationships for nonlinear regressions.INFORMATION SCIENCES,179(12),1929-1943. |
MLA | Hu, Bao-Gang,et al."A generalized-constraint neural network model: Associating partially known relationships for nonlinear regressions".INFORMATION SCIENCES 179.12(2009):1929-1943. |
条目包含的文件 | 条目无相关文件。 |
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。
修改评论