Echo state networks with double-reservoir for time-series prediction

Chong Liu; Huaguang Zhang; Xianshuang Yao; Kun Zhang

doi:10.1109/ICICIP.2016.7885901

Echo state networks with double-reservoir for time-series prediction

Chong Liu
, Huaguang Zhang
, Xianshuang Yao
, Kun Zhang

Northeastern University China

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

6 引用（Scopus）

摘要

In this paper, a novel model, named double-reservoir echo state networks (DR-ESN), is proposed. DR-ESN is constructed by two reservoirs which are connected in series, thus the performance of abstracting the characteristics from the prediction task is improved. A sufficient condition is provided to ensure the stability of DR-ESN. The batch gradient method and ridge regression method are utilized to optimize the six parameters of DR-ESN and train the readouts, respectively. DR-ESN is verified by two different experiments, chaotic time series prediction and real-valued function time series prediction. The simulation results demonstrates that DR-ESN has a more precise result than leaky-ESN in predicting the time series.

源语言	英语
主期刊名	7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings
出版商	Institute of Electrical and Electronics Engineers Inc.
页	196-202
页数	7
ISBN（电子版）	9781509021550
DOI	https://doi.org/10.1109/ICICIP.2016.7885901
出版状态	已出版 - 23 3月 2017
已对外发布	是
活动	7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Siem Reap, 柬埔寨期限: 1 12月 2016 → 4 12月 2016

出版系列

姓名	7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings

会议

会议	7th International Conference on Intelligent Control and Information Processing, ICICIP 2016
国家/地区	柬埔寨
市	Siem Reap
时期	1/12/16 → 4/12/16

访问文件

10.1109/ICICIP.2016.7885901

其它文件与链接

链接到 Scopus 的出版物

引用此

Liu, C., Zhang, H., Yao, X., & Zhang, K. (2017). Echo state networks with double-reservoir for time-series prediction. 在 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings (页码 196-202). 文章 7885901 (7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICICIP.2016.7885901

Liu, Chong ; Zhang, Huaguang ; Yao, Xianshuang 等. / Echo state networks with double-reservoir for time-series prediction. 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. 页码 196-202 (7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings).

@inproceedings{73b09b8976c744faae5f0dcacc02e2dc,

title = "Echo state networks with double-reservoir for time-series prediction",

abstract = "In this paper, a novel model, named double-reservoir echo state networks (DR-ESN), is proposed. DR-ESN is constructed by two reservoirs which are connected in series, thus the performance of abstracting the characteristics from the prediction task is improved. A sufficient condition is provided to ensure the stability of DR-ESN. The batch gradient method and ridge regression method are utilized to optimize the six parameters of DR-ESN and train the readouts, respectively. DR-ESN is verified by two different experiments, chaotic time series prediction and real-valued function time series prediction. The simulation results demonstrates that DR-ESN has a more precise result than leaky-ESN in predicting the time series.",

keywords = "Batch gradient descent, Double-reservoir, Echo state networks, Time-series prediction",

author = "Chong Liu and Huaguang Zhang and Xianshuang Yao and Kun Zhang",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 ; Conference date: 01-12-2016 Through 04-12-2016",

year = "2017",

month = mar,

day = "23",

doi = "10.1109/ICICIP.2016.7885901",

language = "英语",

series = "7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "196--202",

booktitle = "7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings",

address = "美国",

}

Liu, C, Zhang, H, Yao, X & Zhang, K 2017, Echo state networks with double-reservoir for time-series prediction. 在 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings., 7885901, 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 页码 196-202, 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016, Siem Reap, 柬埔寨, 1/12/16. https://doi.org/10.1109/ICICIP.2016.7885901

Echo state networks with double-reservoir for time-series prediction. / Liu, Chong; Zhang, Huaguang; Yao, Xianshuang 等.
7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. 页码 196-202 7885901 (7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings).

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

TY - GEN

T1 - Echo state networks with double-reservoir for time-series prediction

AU - Liu, Chong

AU - Zhang, Huaguang

AU - Yao, Xianshuang

AU - Zhang, Kun

PY - 2017/3/23

Y1 - 2017/3/23

N2 - In this paper, a novel model, named double-reservoir echo state networks (DR-ESN), is proposed. DR-ESN is constructed by two reservoirs which are connected in series, thus the performance of abstracting the characteristics from the prediction task is improved. A sufficient condition is provided to ensure the stability of DR-ESN. The batch gradient method and ridge regression method are utilized to optimize the six parameters of DR-ESN and train the readouts, respectively. DR-ESN is verified by two different experiments, chaotic time series prediction and real-valued function time series prediction. The simulation results demonstrates that DR-ESN has a more precise result than leaky-ESN in predicting the time series.

AB - In this paper, a novel model, named double-reservoir echo state networks (DR-ESN), is proposed. DR-ESN is constructed by two reservoirs which are connected in series, thus the performance of abstracting the characteristics from the prediction task is improved. A sufficient condition is provided to ensure the stability of DR-ESN. The batch gradient method and ridge regression method are utilized to optimize the six parameters of DR-ESN and train the readouts, respectively. DR-ESN is verified by two different experiments, chaotic time series prediction and real-valued function time series prediction. The simulation results demonstrates that DR-ESN has a more precise result than leaky-ESN in predicting the time series.

KW - Batch gradient descent

KW - Double-reservoir

KW - Echo state networks

KW - Time-series prediction

UR - https://www.scopus.com/pages/publications/85018170795

U2 - 10.1109/ICICIP.2016.7885901

DO - 10.1109/ICICIP.2016.7885901

M3 - 会议稿件

AN - SCOPUS:85018170795

T3 - 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings

SP - 196

EP - 202

BT - 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016

Y2 - 1 December 2016 through 4 December 2016

ER -

Liu C, Zhang H, Yao X, Zhang K. Echo state networks with double-reservoir for time-series prediction. 在 7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. 页码 196-202. 7885901. (7th International Conference on Intelligent Control and Information Processing, ICICIP 2016 - Proceedings). doi: 10.1109/ICICIP.2016.7885901

Echo state networks with double-reservoir for time-series prediction

摘要

出版系列

会议

访问文件

其它文件与链接

学术指纹

引用此