EA-LSTM: Evolutionary attention-based LSTM for time series prediction
文献类型：期刊论文
| 作者 | Li, Youru1,2; Zhu, Zhenfeng1,2; Kong, Deqiang3; Han, Hua4,5 ; Zhao, Yao1,2
|
| 刊名 | KNOWLEDGE-BASED SYSTEMS
 |
| 出版日期 | 2019-10-01 |
| 卷号 | 181页码:8 |
| 关键词 | Evolutionary computation Deep neural network Time series prediction |
| ISSN号 | 0950-7051 |
| DOI | 10.1016/j.knosys.2019.05.028 |
| 通讯作者 | Zhu, Zhenfeng(zhfzhu@bjtu.edu.cn) |
| 英文摘要 | Time series prediction with deep learning methods, especially Long Short-term Memory Neural Network (LSTM), have scored significant achievements in recent years. Despite the fact that LSTM can help to capture long-term dependencies, its ability to pay different degree of attention on sub-window feature within multiple time-steps is insufficient. To address this issue, an evolutionary attention-based LSTM training with competitive random search is proposed for multivariate time series prediction. By transferring shared parameters, an evolutionary attention learning approach is introduced to LSTM. Thus, like that for biological evolution, the pattern for importance-based attention sampling can be confirmed during temporal relationship mining. To refrain from being trapped into partial optimization like traditional gradient-based methods, an evolutionary computation inspired competitive random search method is proposed, which can well configure the parameters in the attention layer. Experimental results have illustrated that the proposed model can achieve competetive prediction performance compared with other baseline methods. (C) 2019 Elsevier B.V. All rights reserved. |
| 资助项目 | National Key Research and Development of China[2016YFB0800404] ; National Natural Science Foundation of China[61572068] ; National Natural Science Foundation of China[61532005] ; Special Program of Beijing Municipal Science & Technology Commission[Z181100000118002] ; Strategic Priority Research Program of Chinese Academy of Science[XDB32030200] ; Fundamental Research Funds for the Central Universities of China[2018YJS032] |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000484873600005 |
| 出版者 | ELSEVIER |
| 资助机构 | National Key Research and Development of China ; National Natural Science Foundation of China ; Special Program of Beijing Municipal Science & Technology Commission ; Strategic Priority Research Program of Chinese Academy of Science ; Fundamental Research Funds for the Central Universities of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/27223]  |
| 专题 | 类脑智能研究中心_微观重建与智能分析 |
| 通讯作者 | Zhu, Zhenfeng |
| 作者单位 | 1.Beijing Jiaotong Univ, Inst Informat Sci, Beijing 100044, Peoples R China 2.Beijing Key Lab Adv Informat Sci & Network Techno, Beijing 100044, Peoples R China 3.Microsoft Multimedia, Beijing 100080, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China 5.CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai 200031, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Youru,Zhu, Zhenfeng,Kong, Deqiang,et al. EA-LSTM: Evolutionary attention-based LSTM for time series prediction[J]. KNOWLEDGE-BASED SYSTEMS,2019,181:8. |
| APA | Li, Youru,Zhu, Zhenfeng,Kong, Deqiang,Han, Hua,&Zhao, Yao.(2019).EA-LSTM: Evolutionary attention-based LSTM for time series prediction.KNOWLEDGE-BASED SYSTEMS,181,8. |
| MLA | Li, Youru,et al."EA-LSTM: Evolutionary attention-based LSTM for time series prediction".KNOWLEDGE-BASED SYSTEMS 181(2019):8. |
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。