日本語
 
Privacy Policy ポリシー/免責事項
  詳細検索ブラウズ

アイテム詳細

登録内容を編集ファイル形式で保存
 
 
ダウンロード電子メール
  Embedding theory of reservoir computing and reducing reservoir network using time delays

Duan, X.-Y., Ying, X., Leng, S.-Y., Kurths, J., Lin, W., & Ma, H.-F. (2023). Embedding theory of reservoir computing and reducing reservoir network using time delays. Physical Review Research, 5(2):. doi:10.1103/PhysRevResearch.5.L022041.

Item is

基本情報

表示: 非表示:
資料種別: 学術論文

ファイル

表示: ファイル
非表示: ファイル
:
duan_PhysRevResearch.5.L022041.pdf (出版社版), 3MB
ファイル名:
duan_PhysRevResearch.5.L022041.pdf
説明:
-
閲覧制限:
公開
MIMEタイプ / チェックサム:
application/pdf / [MD5]
技術的なメタデータ:
著作権日付:
-
著作権情報:
-

関連URL

表示:

作成者

表示:
非表示:
 作成者:
Duan, Xing-Yue1, 著者
Ying, Xiong1, 著者
Leng, Si-Yang1, 著者
Kurths, Jürgen2, 著者              
Lin, Wei1, 著者
Ma, Huan-Fei1, 著者
所属:
1External Organizations, ou_persistent22              
2Potsdam Institute for Climate Impact Research, ou_persistent13              

内容説明

表示:
非表示:
キーワード: -
 要旨: Reservoir computing (RC), a particular form of recurrent neural network, is under explosive development due to its exceptional efficacy and high performance in reconstruction and/or prediction of complex physical systems. However, the mechanism triggering such effective applications of RC is still unclear, awaiting deep and systematic exploration. Here, combining the delayed embedding theory with the generalized embedding theory, we rigorously prove that RC is essentially a high-dimensional embedding of the original input nonlinear dynamical system. Thus, using this embedding property, we unify into a universal framework the standard RC and the time-delayed RC where we introduce time delays only into the network's output layer, and we further find a trade-off relation between the time delays and the number of neurons in RC. Based on these findings, we significantly reduce the RC's network size and promote its memory capacity in completing systems reconstruction and prediction. More surprisingly, only using a single-neuron reservoir with time delays is sometimes sufficient for achieving reconstruction and prediction tasks, while the standard RC of any large size but without time delay cannot complete them yet.

資料詳細

表示:
非表示:
言語: eng - 英語
 日付: 2023-05-252023-07-01
 出版の状態: Finally published
 ページ: 6
 出版情報: -
 目次: -
 査読: 査読あり
 識別子(DOI, ISBNなど): DOI: 10.1103/PhysRevResearch.5.L022041
MDB-ID: No data to archive
PIKDOMAIN: RD4 - Complexity Science
Organisational keyword: RD4 - Complexity Science
Research topic keyword: Complex Networks
Research topic keyword: Nonlinear Dynamics
Model / method: Machine Learning
OATYPE: Gold Open Access
 学位: -

関連イベント

表示:

訴訟

表示:

Project information

表示:

出版物 1

表示:
非表示:
出版物名: Physical Review Research
種別: 学術雑誌, other, oa
 著者・編者:
所属:
出版社, 出版地: -
ページ: - 巻号: 5 (2) 通巻号: L022041 開始・終了ページ: - 識別子(ISBN, ISSN, DOIなど): CoNE: https://publications.pik-potsdam.de/cone/journals/resource/20200302
Publisher: American Physical Society (APS)