Standard

Research on Hierarchical Reservoir Neural Network. / Tarkov, Mikhail S.; Jing, Ma.

Studies in Computational Intelligence. ed. / Janusz Kacprzyk. Vol. 1179 SCI Springer, 2025. p. 3-12 1 (Studies in Computational Intelligence; Vol. 1179 SCI).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review

Harvard

Tarkov, MS & Jing, M 2025, Research on Hierarchical Reservoir Neural Network. in J Kacprzyk (ed.), Studies in Computational Intelligence. vol. 1179 SCI, 1, Studies in Computational Intelligence, vol. 1179 SCI, Springer, pp. 3-12, 26th International Conference on Neuroinformatics, Москва, Russian Federation, 21.10.2024. https://doi.org/10.1007/978-3-031-80463-2_1

APA

Tarkov, M. S., & Jing, M. (2025). Research on Hierarchical Reservoir Neural Network. In J. Kacprzyk (Ed.), Studies in Computational Intelligence (Vol. 1179 SCI, pp. 3-12). [1] (Studies in Computational Intelligence; Vol. 1179 SCI). Springer. https://doi.org/10.1007/978-3-031-80463-2_1

Vancouver

Tarkov MS, Jing M. Research on Hierarchical Reservoir Neural Network. In Kacprzyk J, editor, Studies in Computational Intelligence. Vol. 1179 SCI. Springer. 2025. p. 3-12. 1. (Studies in Computational Intelligence). doi: 10.1007/978-3-031-80463-2_1

Author

Tarkov, Mikhail S. ; Jing, Ma. / Research on Hierarchical Reservoir Neural Network. Studies in Computational Intelligence. editor / Janusz Kacprzyk. Vol. 1179 SCI Springer, 2025. pp. 3-12 (Studies in Computational Intelligence).

BibTeX

@inproceedings{4a0c3b2f52fc4f7a89ccadc5a366687a,
title = "Research on Hierarchical Reservoir Neural Network",
abstract = "Echo State Network (ESN) is an effective replacement for recurrent neural networks as a reservoir computing model. Similar to deep neural networks, adding hierarchical structure to an ESN is an effective way to improve the network efficiency. The paper examines the influence of the reservoir hierarchical structure on the network efficiency depending on the number of subreservoirs and the number of nodes in the reservoir, and also considers three main hyperparameters that influence the reservoir efficiency: leakage rate, spectral radius and input scale factor. To test the network efficiency, Mackey-Glass time series and power transformer data were selected as experimental data. Experimental results show that the reservoir hierarchical structure improves the prediction accuracy and reduces the computation time for the ESN model.",
keywords = "hierarchical ESN, recurrent neural networks, reservoir",
author = "Tarkov, {Mikhail S.} and Ma Jing",
year = "2025",
doi = "10.1007/978-3-031-80463-2_1",
language = "English",
isbn = "978-303180462-5",
volume = "1179 SCI",
series = "Studies in Computational Intelligence",
publisher = "Springer",
pages = "3--12",
editor = "Janusz Kacprzyk",
booktitle = "Studies in Computational Intelligence",
address = "United States",
note = "26th International Conference on Neuroinformatics, NI 2024 ; Conference date: 21-10-2024 Through 25-10-2024",

}

RIS

TY - GEN

T1 - Research on Hierarchical Reservoir Neural Network

AU - Tarkov, Mikhail S.

AU - Jing, Ma

N1 - Conference code: 26

PY - 2025

Y1 - 2025

N2 - Echo State Network (ESN) is an effective replacement for recurrent neural networks as a reservoir computing model. Similar to deep neural networks, adding hierarchical structure to an ESN is an effective way to improve the network efficiency. The paper examines the influence of the reservoir hierarchical structure on the network efficiency depending on the number of subreservoirs and the number of nodes in the reservoir, and also considers three main hyperparameters that influence the reservoir efficiency: leakage rate, spectral radius and input scale factor. To test the network efficiency, Mackey-Glass time series and power transformer data were selected as experimental data. Experimental results show that the reservoir hierarchical structure improves the prediction accuracy and reduces the computation time for the ESN model.

AB - Echo State Network (ESN) is an effective replacement for recurrent neural networks as a reservoir computing model. Similar to deep neural networks, adding hierarchical structure to an ESN is an effective way to improve the network efficiency. The paper examines the influence of the reservoir hierarchical structure on the network efficiency depending on the number of subreservoirs and the number of nodes in the reservoir, and also considers three main hyperparameters that influence the reservoir efficiency: leakage rate, spectral radius and input scale factor. To test the network efficiency, Mackey-Glass time series and power transformer data were selected as experimental data. Experimental results show that the reservoir hierarchical structure improves the prediction accuracy and reduces the computation time for the ESN model.

KW - hierarchical ESN

KW - recurrent neural networks

KW - reservoir

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-105000231955&origin=inward&txGid=4bb22898968f34bfb04243f8acfcde1b

UR - https://www.mendeley.com/catalogue/fa357b69-c575-39b0-97d1-9552eaa86f66/

U2 - 10.1007/978-3-031-80463-2_1

DO - 10.1007/978-3-031-80463-2_1

M3 - Conference contribution

SN - 978-303180462-5

VL - 1179 SCI

T3 - Studies in Computational Intelligence

SP - 3

EP - 12

BT - Studies in Computational Intelligence

A2 - Kacprzyk, Janusz

PB - Springer

T2 - 26th International Conference on Neuroinformatics

Y2 - 21 October 2024 through 25 October 2024

ER -

ID: 65253602