| Regularized Taylor Echo State Networks for Predictive Control of Partially Observed Systems | |
Xiang, Kui1; Li, Bing Nan2; Zhang, Liyan1; Pang, Muye1; Wang, Meng3; Li, Xuelong4 ; Li, Bing Nan (bingoon@ieee.org)
| |
| 作者部门 | 光学影像学习与分析中心 |
| 2016 | |
| 发表期刊 | IEEE ACCESS
 |
| ISSN | 2169-3536 |
| 卷号 | 4页码:3300-3309 |
| 产权排序 | 4 |
| 摘要 | The existing neural networks suffer from partial observation while modeling and controlling dynamic systems. In this paper, a new linearized recurrent neural network, the Taylor expanded echo state network (TESN), is proposed for predictive control of partially observed dynamic systems. Two schemes of regularization, ridge regression and sparse regression, are imposed on TESNs to tackle the issue of ill-conditioned estimation. Furthermore, two estimators, lasso and elastic net, are investigated for sparse regression. Regularized learning is found to improve the estimation consistency of readout coefficients and, at the same time, suppress the accumulation of linearization residues in a prediction horizon. A series of experiments was carried out, and the results verified that regularized learning is contributive to TESNs in predictive control of partially observed dynamic systems. |
| 文章类型 | Article |
| 关键词 | Neural Networks Echo State Networks Sparse Regularization Predictive Control |
| WOS标题词 | Science & Technology ; Technology |
| DOI | 10.1109/ACCESS.2016.2582478 |
| 收录类别 | SCI ; EI |
| 关键词[WOS] | RECURRENT NEURAL-NETWORKS ; NONLINEAR-SYSTEMS ; SELECTION ; REGRESSION ; IDENTIFICATION ; RECOGNITION |
| 语种 | 英语 |
| WOS研究方向 | Computer Science ; Engineering ; Telecommunications |
| 项目资助者 | State Key Laboratory of Transient Optics and Photonics(1503062015) ; Anhui Provincial Natural Science Foundation(1608085J04) ; National Natural Science Foundation of China(61271123 ; 61571176 ; 61511140099) |
| WOS类目 | Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications |
| WOS记录号 | WOS:000380337900002 |
| 引用统计 | |
| 文献类型 | 期刊论文 |
| 条目标识符 | http://ir.opt.ac.cn/handle/181661/28194 |
| 专题 | 光谱成像技术研究室 |
| 通讯作者 | Li, Bing Nan (bingoon@ieee.org) |
| 作者单位 | 1.Wuhan Univ Technol, Sch Automat, Wuhan 430070, Peoples R China 2.Hefei Univ Technol, Sch Instrument Sci & Optoelect Engn, Hefei 230009, Peoples R China 3.Hefei Univ Technol, Sch Comp & Informat, Hefei 230009, Peoples R China 4.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Ctr Optic Imagery Anal & Learning, State Key Lab Transient Opt & Photon, Xian 710119, Peoples R China |
| 推荐引用方式 GB/T 7714 | Xiang, Kui,Li, Bing Nan,Zhang, Liyan,et al. Regularized Taylor Echo State Networks for Predictive Control of Partially Observed Systems[J]. IEEE ACCESS,2016,4:3300-3309. |
| APA | Xiang, Kui.,Li, Bing Nan.,Zhang, Liyan.,Pang, Muye.,Wang, Meng.,...&Li, Bing Nan .(2016).Regularized Taylor Echo State Networks for Predictive Control of Partially Observed Systems.IEEE ACCESS,4,3300-3309. |
| MLA | Xiang, Kui,et al."Regularized Taylor Echo State Networks for Predictive Control of Partially Observed Systems".IEEE ACCESS 4(2016):3300-3309. |
| 条目包含的文件 | ||||||
| 文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
| Regularized Taylor E（5356KB） | 期刊论文 | 作者接受稿 | 限制开放 | CC BY-NC-SA | 请求全文 | |
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