A machine-learning approach called "reservoir computing" has been used successfully for short-term prediction and attractor reconstruction of chaotic dynamical systems from time series data. We present a theoretical framework that describes conditions under which reservoir computing can create an empirical model capable of skillful short-term forecasts and accurate long-term ergodic behavior. We illustrate this theory through numerical experiments. We also argue that the theory applies to certain other machine learning methods for time series prediction.
Slow-spectrum preshaping for reservoir computing: Attractor reconstruction in attracting submanifolds under partial observation
Graduate School of Information Science and Technology, The University of Osaka(大阪大学信息理工学研究科);International Research Center for Neurointelligence, The University of Tokyo(东京大学国际神经智能研究中心)
Institut für KI-Sicherheit, Deutsches Zentrum für Luft- und Raumfahrt (DLR)(德国航空航天中心人工智能安全研究所);Ludwig-Maximilians-Universität (LMU)(慕尼黑大学);University College Cork(科克大学);INFANT Research Centre, University College Cork(科克大学INFANT研究中心);Institut für Frontier Materials auf der Erde und im Weltraum, Deutsches Zentrum für Luft- und Raumfahrt (DLR)(德国航空航天中心地外前沿材料研究所)
The Ohio State University(俄亥俄州立大学);ResCon Technologies LLC(ResCon技术有限责任公司);Instituto de Física Interdisciplinar y Sistemas Complejos, IFISC (CSIC-UIB)(跨学科物理与复杂系统研究所(IFISC,西班牙国家研究委员会-巴利阿里群岛大学));The University of Tokyo(东京大学)
On the attractor in a high-dimensional neural network dynamics of reservoir computing: Lyapunov analysis viewpoint
Faculty of Economics, Rissho University(立教大学经济学部);Graduate School of Environment, Life, Natural Science and Technology, Okayama University(冈山大学环境·生命·自然科学和技术研究院);Graduate School of Business Administration, Hitotsubashi University(一桥大学商学研究科)
Denoising and Reconstruction of Nonlinear Dynamics using Truncated Reservoir Computing
Centre for Audio, Acoustics and Vibration (CAAV), School of Mechanical and Mechatronic Engineering, University of Technology Sydney, Ultimo, NSW 2007, Australia(音频、声学与振动中心(CAAV),机械与机电工程学院,悉尼技术大学,Ultimo,新南威尔士州2007,澳大利亚)