Analysis of Reservoir Computing Focusing on the Spectrum of Bistable Delayed Dynamical Systems

• Kinoshita Ikuhide

  Graduate School of Engineering, The University of Tokyo

• Akao Akihiko

  Graduate School of Engineering, The University of Tokyo

• Shirasaka Sho

  Research Center for Advanced Science and Technology, The University of Tokyo

• Kotani Kiyoshi

  Graduate School of Engineering, The University of Tokyo Research Center for Advanced Science and Technology, The University of Tokyo JST, PRESTO

• Jimbo Yasuhiko

  Graduate School of Engineering, The University of Tokyo

Bibliographic Information

Other Title

• 双安定な時間遅れ力学系のスペクトルに着目したReservoir Computingの解析
• ソウアンテイ ナ ジカン オクレ リキガクケイ ノ スペクトル ニ チャクモク シタ Reservoir Computing ノ カイセキ

Abstract

Reservoir Computing (RC) is a machine-learning paradigm that is capable to process empirical time-series data. This paradigm is based on a neural network with a fixed hidden layer having a high-dimensional state space, called a reservoir. Reservoirs including time-delays are considered to be good candidates for practical applications because they make hardware realization of the high-dimensional reservoirs simple. Performance of the well-trained RCs depends both on dynamical properties of attractors of the reservoirs and tasks they solve. Therefore, in the conventional monostable RCs, there arise task-wise optimization problems of the reservoirs, which have been solved based on trial and error approaches. In this study, we analyzed the relationship between the dynamical properties of the time-delay reservoir and the performance in terms of the spectra of the delayed dynamical systems, which might facilitate the development of the unified systematic optimization techniques for the time-delay reservoirs. In addition, we propose a novel RC framework that performs well on distinct tasks without the task-wise optimization using bistable reservoir dynamics which can reduce complicated hardware management of the reservoirs.

Journal

• IEEJ Transactions on Electronics, Information and Systems

  IEEJ Transactions on Electronics, Information and Systems 138 (8), 1054-1059, 2018-08-01

  The Institute of Electrical Engineers of Japan

Keywords

• reservoir computing
• delayed dynamical systems
• bistable systems

Details

• CRID: 1390001288050165376
• NII Article ID: 130007429818
• NII Book ID: AN10065950
• DOI: 10.1541/ieejeiss.138.1054
• ISSN: 13488155
• ISSN: 03854221
• NDL BIB ID: 029197406
• Web Site: https://ndlsearch.ndl.go.jp/books/R000000004-I029197406
• Web Site: https://www.jstage.jst.go.jp/article/ieejeiss/138/8/138_1054/_pdf
• Text Lang: ja
• Data Source:
  • JaLC
  • NDL
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed