Simulation Study of Physical Reservoir Computing by Nonlinear Deterministic Time Series Analysis

被引：3

作者：

Yamane, Toshiyuki ^{[1
]}

Takeda, Seiji ^{[1
]}

Nakano, Daiju ^{[1
]}

Tanaka, Gouhei ^{[2
]}

Nakane, Ryosho ^{[2
]}

Hirose, Akira ^{[2
]}

Nakagawa, Shigeru ^{[1
]}

机构：

[1] IBM Res Tokyo, Kawasaki, Kanagawa 2120032, Japan

[2] Univ Tokyo, Grad Sch Engn, Tokyo 1138656, Japan

来源：

NEURAL INFORMATION PROCESSING, ICONIP 2017, PT I | 2017年 / 10634卷

关键词：

Reservoir computing; Physical reservoir; Bifurcation phenomena; Takens' theorem; False nearest neighbours; Lang-Kobayashi equation;

D O I：

10.1007/978-3-319-70087-8_66

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We investigate dynamics of physical reservoir computing by numerical simulations. Our approach is based on nonlinear deterministic time series analysis such as Takens' theorem and false nearest neighbor methods. We show that this approach is useful for efficient design and implementation of physical reservoir computing systems where only partial information of the reservoir state is accessible. We take nonlinear laser dynamics subject to time delay as physical reservoir and show that the size of physical reservoir can be estimated by these method.

引用

页码：639 / 647

页数：9

共 50 条

[1] Parameter extraction with reservoir computing: Nonlinear time series analysis and application to industrial maintenance
Thorne, Braden
Jungling, Thomas
Small, Michael
Hodkiewicz, Melinda
CHAOS, 2021, 31 (03)
[2] Second-order Time Delay Reservoir Computing for Nonlinear Time Series Problems
Shi, Xinming
Gao, Jiashi
Minku, Leandro L.
Yu, James J. Q.
Yao, Xin
2021 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2021), 2021,
[3] Time series analysis for financial indices using optical reservoir computing
Qu Y.
Lian H.
Shao R.
Liu J.
Liu L.
Yang J.
Optical Engineering, 2024, 63 (05) : 54108
[4] Fractional integration and nonlinear deterministic trends in the analysis of time series data
Gil-Alana, Luis A.
Carcel, Hector
APPLIED ECONOMICS LETTERS, 2017, 24 (14) : 991 - 994
[5] A comparative study of Reservoir Computing strategies for monthly time series prediction
Wyffels, F.
Schrauwen, B.
NEUROCOMPUTING, 2010, 73 (10-12) : 1958 - 1964
[6] Reservoir Computing Hardware for Time Series Forecasting
Skibinsky-Gitlin, E. S.
Alomar, M. L.
Isern, E.
Roca, M.
Canals, V.
Rossello, J. L.
2018 28TH INTERNATIONAL SYMPOSIUM ON POWER AND TIMING MODELING, OPTIMIZATION AND SIMULATION (PATMOS), 2018, : 133 - 139
[7] Time Series Clustering with Deep Reservoir Computing
Atencia, Miguel
Gallicchio, Claudio
Joya, Gonzalo
Micheli, Alessio
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2020, PT II, 2020, 12397 : 482 - 493
[8] Nonlinear Time Series Analysis: A High Performance Computing Approach
Marin Carrion, Ismael
Aguila Guerrero, Julio Jose
Arias Antunez, Enrique
Artigao Castillo, Maria del Mar
Miralles Canals, Juan Jose
ERCIM NEWS, 2010, (81): : 31 - 32
[9] Feedback-Driven Quantum Reservoir Computing for Time-Series Analysis
Kobayashi, Kaito
Fujii, Keisuke
Yamamoto, Naoki
PRX Quantum, 2024, 5 (04):
[10] Multivariate nonlinear time-series estimation using delay-based reservoir computing
Escalona-Moran, M.
Soriano, M. C.
Garcia-Prieto, J.
Fischer, I.
Mirasso, C. R.
EUROPEAN PHYSICAL JOURNAL-SPECIAL TOPICS, 2014, 223 (13): : 2903 - 2912

← 1 2 3 4 5 →