Standard
Time Series Prediction by Reservoir Neural Networks. / Tarkov, Mikhail S.; Chernov, Ivan A.
Advances in Neural Computation, Machine Learning, and Cognitive Research IV - Selected Papers from the 22nd International Conference on Neuroinformatics, 2020. ed. / Boris Kryzhanovsky; Witali Dunin-Barkowski; Vladimir Redko; Yury Tiumentsev. Springer Science and Business Media Deutschland GmbH, 2021. p. 303-308 (Studies in Computational Intelligence; Vol. 925 SCI).
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
Harvard
Tarkov, MS & Chernov, IA 2021,
Time Series Prediction by Reservoir Neural Networks. in B Kryzhanovsky, W Dunin-Barkowski, V Redko & Y Tiumentsev (eds),
Advances in Neural Computation, Machine Learning, and Cognitive Research IV - Selected Papers from the 22nd International Conference on Neuroinformatics, 2020. Studies in Computational Intelligence, vol. 925 SCI, Springer Science and Business Media Deutschland GmbH, pp. 303-308, 22nd International Conference on Neuroinformatics, 2020, Moscow, Russian Federation,
12.10.2020.
https://doi.org/10.1007/978-3-030-60577-3_36
APA
Tarkov, M. S., & Chernov, I. A. (2021).
Time Series Prediction by Reservoir Neural Networks. In B. Kryzhanovsky, W. Dunin-Barkowski, V. Redko, & Y. Tiumentsev (Eds.),
Advances in Neural Computation, Machine Learning, and Cognitive Research IV - Selected Papers from the 22nd International Conference on Neuroinformatics, 2020 (pp. 303-308). (Studies in Computational Intelligence; Vol. 925 SCI). Springer Science and Business Media Deutschland GmbH.
https://doi.org/10.1007/978-3-030-60577-3_36
Vancouver
Tarkov MS, Chernov IA.
Time Series Prediction by Reservoir Neural Networks. In Kryzhanovsky B, Dunin-Barkowski W, Redko V, Tiumentsev Y, editors, Advances in Neural Computation, Machine Learning, and Cognitive Research IV - Selected Papers from the 22nd International Conference on Neuroinformatics, 2020. Springer Science and Business Media Deutschland GmbH. 2021. p. 303-308. (Studies in Computational Intelligence). doi: 10.1007/978-3-030-60577-3_36
Author
Tarkov, Mikhail S. ; Chernov, Ivan A. /
Time Series Prediction by Reservoir Neural Networks. Advances in Neural Computation, Machine Learning, and Cognitive Research IV - Selected Papers from the 22nd International Conference on Neuroinformatics, 2020. editor / Boris Kryzhanovsky ; Witali Dunin-Barkowski ; Vladimir Redko ; Yury Tiumentsev. Springer Science and Business Media Deutschland GmbH, 2021. pp. 303-308 (Studies in Computational Intelligence).
BibTeX
@inproceedings{de60e2c5c9ec4d5cbb390a5aa243864a,
title = "Time Series Prediction by Reservoir Neural Networks",
abstract = "The tasks of forecasting time series arise in many areas of computer science. Algorithms based on machine learning do a good job of this task. In this work, we performed a comparative analysis of a number of algorithms for predicting time series by reservoir neural networks (echo-state networks) according to the forecast accuracy and the time it takes to build the forecast. To test forecasting algorithms, data sets obtained from the Mackey-Glass equation were used. The experiments showed that the sigmoidal and radial networks with a SOM projector give the most accurate forecast, but they are also the least fast. A new reservoir optimization algorithm is proposed - a direct version of the Infomax method. The functionality of the mutual information of the input and output of the reservoir is maximized. This algorithm requires non-negativity of data values, but it works much faster than the well-known iterative version of Infomax and a radial network with a SOM projector, although it slightly reduces the forecast accuracy.",
keywords = "Forecast, Maximization of mutual information, Reservoir neural networks, Time series",
author = "Tarkov, {Mikhail S.} and Chernov, {Ivan A.}",
year = "2021",
doi = "10.1007/978-3-030-60577-3_36",
language = "English",
isbn = "9783030605766",
series = "Studies in Computational Intelligence",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "303--308",
editor = "Boris Kryzhanovsky and Witali Dunin-Barkowski and Vladimir Redko and Yury Tiumentsev",
booktitle = "Advances in Neural Computation, Machine Learning, and Cognitive Research IV - Selected Papers from the 22nd International Conference on Neuroinformatics, 2020",
address = "Germany",
note = "22nd International Conference on Neuroinformatics, 2020 ; Conference date: 12-10-2020 Through 16-10-2020",
}
RIS
TY - GEN
T1 - Time Series Prediction by Reservoir Neural Networks
AU - Tarkov, Mikhail S.
AU - Chernov, Ivan A.
PY - 2021
Y1 - 2021
N2 - The tasks of forecasting time series arise in many areas of computer science. Algorithms based on machine learning do a good job of this task. In this work, we performed a comparative analysis of a number of algorithms for predicting time series by reservoir neural networks (echo-state networks) according to the forecast accuracy and the time it takes to build the forecast. To test forecasting algorithms, data sets obtained from the Mackey-Glass equation were used. The experiments showed that the sigmoidal and radial networks with a SOM projector give the most accurate forecast, but they are also the least fast. A new reservoir optimization algorithm is proposed - a direct version of the Infomax method. The functionality of the mutual information of the input and output of the reservoir is maximized. This algorithm requires non-negativity of data values, but it works much faster than the well-known iterative version of Infomax and a radial network with a SOM projector, although it slightly reduces the forecast accuracy.
AB - The tasks of forecasting time series arise in many areas of computer science. Algorithms based on machine learning do a good job of this task. In this work, we performed a comparative analysis of a number of algorithms for predicting time series by reservoir neural networks (echo-state networks) according to the forecast accuracy and the time it takes to build the forecast. To test forecasting algorithms, data sets obtained from the Mackey-Glass equation were used. The experiments showed that the sigmoidal and radial networks with a SOM projector give the most accurate forecast, but they are also the least fast. A new reservoir optimization algorithm is proposed - a direct version of the Infomax method. The functionality of the mutual information of the input and output of the reservoir is maximized. This algorithm requires non-negativity of data values, but it works much faster than the well-known iterative version of Infomax and a radial network with a SOM projector, although it slightly reduces the forecast accuracy.
KW - Forecast
KW - Maximization of mutual information
KW - Reservoir neural networks
KW - Time series
UR - http://www.scopus.com/inward/record.url?scp=85093092403&partnerID=8YFLogxK
UR - https://www.mendeley.com/catalogue/42b48358-a880-3f68-9011-c04082457209/
U2 - 10.1007/978-3-030-60577-3_36
DO - 10.1007/978-3-030-60577-3_36
M3 - Conference contribution
AN - SCOPUS:85093092403
SN - 9783030605766
T3 - Studies in Computational Intelligence
SP - 303
EP - 308
BT - Advances in Neural Computation, Machine Learning, and Cognitive Research IV - Selected Papers from the 22nd International Conference on Neuroinformatics, 2020
A2 - Kryzhanovsky, Boris
A2 - Dunin-Barkowski, Witali
A2 - Redko, Vladimir
A2 - Tiumentsev, Yury
PB - Springer Science and Business Media Deutschland GmbH
T2 - 22nd International Conference on Neuroinformatics, 2020
Y2 - 12 October 2020 through 16 October 2020
ER -