Oscillations enhance time-series prediction in reservoir computing with feedback

Kawai, Yuji; Morita, Takashi; Park, Jihoon; Asada, Minoru

doi:https://doi.org/10.1016/j.neucom.2025.130728

Oscillations enhance time-series prediction in reservoir computing with feedback

Kawai, Yuji; Morita, Takashi; Park, Jihoon et al.

Neurocomputing, 2025, 648, 130728

アクセス数:6件（2025-09-04 12:23 集計）

固定URL: https://hdl.handle.net/11094/102623

閲覧可能ファイル

ファイル	フォーマット	利用条件	サイズ	閲覧回数	利用開始日	説明	information
Neurocomputing_648	pdf	なし	55.0 MB	13	2025.08.29

Creative Commons : 表示

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	Oscillations enhance time-series prediction in reservoir computing with feedback
著者	NRID 1000060791291 1000060791291 ORCID 0000-0002-9976-4195 0000-0002-9976-4195 researchmap permalink yujikawai yujikawai Scopus Author ID 53879989900 53879989900 著者名 Kawai, Yuji
	NRID 1000010837587 1000010837587 著者名 Morita, Takashi
	NRID 1000030790836 1000030790836 ORCID 0000-0003-3582-204X 0000-0003-3582-204X researchmap permalink jihoon_park jihoon_park Scopus Author ID 55843891100 55843891100 著者名 Park, Jihoon
	NRID 1000060151031 1000060151031 researchmap permalink minoruasada minoruasada Scopus Author ID 55843502400 55843502400 ORCID 0000-0001-9506-6333 0000-0001-9506-6333 著者名 Asada, Minoru
キーワード等	Chaotic time series
	Oscillation
	Recurrent neural network
	Reservoir computing
	Timing learning
内容	Kawai Y., Morita T., Park J., et al. Oscillations enhance time-series prediction in reservoir computing with feedback. Neurocomputing 648, 130728 (2025); https://doi.org/10.1016/j.neucom.2025.130728.
抄録	Reservoir computing, a machine learning framework used for modeling the brain, can predict temporal data with little observations and minimal computational resources. However, it is difficult to accurately reproduce the long-term target time series because the reservoir system becomes unstable. This predictive capability is required for a wide variety of time-series processing, including predictions of motor timing and chaotic dynamical systems. This study proposes oscillation-driven reservoir computing (ODRC) with feedback, where oscillatory signals are fed into a reservoir network to stabilize the network activity and induce complex reservoir dynamics. The ODRC can reproduce long-term target time series more accurately than conventional reservoir computing methods in a motor timing and chaotic time-series prediction tasks. Furthermore, it generates a time series similar to the target in the unexperienced period, that is, it can learn the abstract generative rules from limited observations. Given these significant improvements made by the simple and computationally inexpensive implementation, the ODRC would serve as a practical model of various time series data. Moreover, we will discuss biological implications of the ODRC, considering it as a model of neural oscillations and their cerebellar processors.
出版者	Elsevier B.V.
収録物名	Neurocomputing
巻(号)	648
ページ	130728
刊行年月	2025-06-21
言語	英語
ハンドルURL	https://hdl.handle.net/11094/102623
PISSN	09252312
eISSN	18728286
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.1016/j.neucom.2025.130728
アクセス権	open access
権利情報	This article is licensed under a Creative Commons Attribution 4.0 International License.
出版タイプ	Version of Record
カテゴリ	学術雑誌論文 Journal Article

資源タイプ	学術雑誌論文
ローカル資源タイプ	学術雑誌論文
DCMI資源タイプ	text
DCTERMS.bibliographicCitation	Neurocomputing. 2025, 648, p. 130728
DC.title	Oscillations enhance time-series prediction in reservoir computing with feedback
DC.creator	Kawai, Yuji
	Morita, Takashi
	Park, Jihoon
	Asada, Minoru
DC.publisher	Elsevier B.V.
DC.language' scheme='DCTERMS.RFC1766	英語
DC.type' scheme='DCTERMS.DCMIType	text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2025-06-21
DC.identifier	https://doi.org/10.1016/j.neucom.2025.130728
DC.subject	Chaotic time series
	Oscillation
	Recurrent neural network
	Reservoir computing
	Timing learning
DC.description	Kawai Y., Morita T., Park J., et al. Oscillations enhance time-series prediction in reservoir computing with feedback. Neurocomputing 648, 130728 (2025); https://doi.org/10.1016/j.neucom.2025.130728.
DCTERMS.abstract	Reservoir computing, a machine learning framework used for modeling the brain, can predict temporal data with little observations and minimal computational resources. However, it is difficult to accurately reproduce the long-term target time series because the reservoir system becomes unstable. This predictive capability is required for a wide variety of time-series processing, including predictions of motor timing and chaotic dynamical systems. This study proposes oscillation-driven reservoir computing (ODRC) with feedback, where oscillatory signals are fed into a reservoir network to stabilize the network activity and induce complex reservoir dynamics. The ODRC can reproduce long-term target time series more accurately than conventional reservoir computing methods in a motor timing and chaotic time-series prediction tasks. Furthermore, it generates a time series similar to the target in the unexperienced period, that is, it can learn the abstract generative rules from limited observations. Given these significant improvements made by the simple and computationally inexpensive implementation, the ODRC would serve as a practical model of various time series data. Moreover, we will discuss biological implications of the ODRC, considering it as a model of neural oscillations and their cerebellar processors.
DC.rights	This article is licensed under a Creative Commons Attribution 4.0 International License.
DC.format	102623
citation_title	Oscillations enhance time-series prediction in reservoir computing with feedback
citation_author	Kawai, Yuji
	Morita, Takashi
	Park, Jihoon
	Asada, Minoru
citation_publisher	Elsevier B.V.
citation_language	英語
citation_date	2025-06-21
citation_journal_title	Neurocomputing
citation_volume	648
citation_firstpage	130728
citation_doi	https://doi.org/10.1016/j.neucom.2025.130728
citation_public_url	https://hdl.handle.net/11094/102623

Oscillations enhance time-series prediction in reservoir computing with feedback

閲覧可能ファイル

論文情報

論文詳細を表示