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

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2018/08/01

タイトル(英語): Analysis of Reservoir Computing Focusing on the Spectrum of Bistable Delayed Dynamical Systems

著者名: 木下　郁英（東京大学大学院工学系研究科），赤尾　旭彦（東京大学大学院工学系研究科），白坂　将（東京大学先端科学技術研究センター），小谷　潔（東京大学大学院工学系研究科／東京大学先端科学技術研究センター／独立行政法人科学技術振興機構, さきがけ），神保　泰彦（東京大学大学院工学系研究科）

著者名(英語): Ikuhide Kinoshita (Graduate School of Engineering, The University of Tokyo), Akihiko Akao (Graduate School of Engineering, The University of Tokyo), Sho Shirasaka (Research Center for Advanced Science and Technology, The University of Tokyo), Kiyoshi Kota

キーワード: リザーバコンピューティング，時間遅れ力学系，双安定系_x000D_　　reservoir computing，delayed dynamical systems，bistable systems

要約(英語): 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.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.138 No.8 （2018） 特集：人間と情報を繋ぐ情報システム

本誌掲載ページ: 1054-1059 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/138/8/138_1054/_article/-char/ja/