Geometric interpretation of nonlinear approximation capability for feedforward neural networks
文献类型：期刊论文
| 作者 | Hu, BG ; Xing, HJ; Yang, YJ; Yin, FL; Wang, J; Guo, CG
|
| 刊名 | ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 1
 |
| 出版日期 | 2004 |
| 卷号 | 3173页码:7-13 |
| 英文摘要 | This paper presents a preliminary study on the nonlinear approximation capability of feedforward neural networks (FNNs) via a geometric approach. Three simplest FNNs with at most four free parameters are defined and investigated. By approximations on one-dimensional functions, we observe that the Chebyshev-polynomials, Gaussian, and sigmoidal FNNs are ranked in order of providing more varieties of non-linearities. If neglecting the compactness feature inherited by Gaussian neural networks, we consider that the Chebyshev-polynomial-based neural networks will be the best among three types of FNNs in an efficient use of free parameters. |
| WOS标题词 | Science & Technology ; Technology |
| 类目[WOS] | Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods |
| 研究领域[WOS] | Computer Science |
| 收录类别 | ISTP ; SCI |
| 语种 | 英语 |
| WOS记录号 | WOS:000223492600002 |
| 公开日期 | 2015-09-22 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/7980]  |
| 专题 | 自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队 |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100080, Peoples R China 2.Chinese Acad Sci, Beijing Grad Sch, Beijing 100080, Peoples R China |
| 推荐引用方式 GB/T 7714 | Hu, BG,Xing, HJ,Yang, YJ,et al. Geometric interpretation of nonlinear approximation capability for feedforward neural networks[J]. ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 1,2004,3173:7-13. |
| APA | Hu, BG,Xing, HJ,Yang, YJ,Yin, FL,Wang, J,&Guo, CG.(2004).Geometric interpretation of nonlinear approximation capability for feedforward neural networks.ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 1,3173,7-13. |
| MLA | Hu, BG,et al."Geometric interpretation of nonlinear approximation capability for feedforward neural networks".ADVANCES IN NEURAL NETWORKS - ISNN 2004, PT 1 3173(2004):7-13. |
入库方式： OAI收割
来源：自动化研究所
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。