Learning Coupled Oscillators System with Reservoir Computing

被引:6
作者
Zhong, Xijuan [1 ]
Wang, Shuai [1 ]
机构
[1] Changchun Univ Sci & Technol, Sch Math & Stat, Changchun 130000, Peoples R China
来源
SYMMETRY-BASEL | 2022年 / 14卷 / 06期
关键词
reservoir computing; coupled Lorenz system; rotating periodic solution; synchronous chaos; invariant torus; ROTATING-PERIODIC-SOLUTIONS; SYNCHRONIZED MOTION; STABILITY THEORY; WAVES;
D O I
10.3390/sym14061084
中图分类号
O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];
学科分类号
07 ; 0710 ; 09 ;
摘要
In this paper, we reconstruct the dynamic behavior of the ring-coupled Lorenz oscillators system by reservoir computing. Although the reconstruction of various complex chaotic attractors has been well studied by using various neural networks, little attention has been paid to whether the spatio-temporal structure of some special attractors can be maintained in long-term prediction. Reservoir computing has been shown to be effective for model-free prediction, so we want to investigate whether reservoir computing can restore the rotational symmetry of the original ring-coupled Lorenz system. We find that although the state prediction of the trained reservoir computer will gradually deviate from the actual trajectory of the original system, the associated spatio-temporal structure is maintained in the process of reconstruction. Specifically, we show that the rotational symmetric structure of periodic rotating waves, quasi-periodic torus, and chaotic rotating waves is well maintained.
引用
收藏
页数:14
相关论文
共 34 条
[1]   The synchronization of chaotic systems [J].
Boccaletti, S ;
Kurths, J ;
Osipov, G ;
Valladares, DL ;
Zhou, CS .
PHYSICS REPORTS-REVIEW SECTION OF PHYSICS LETTERS, 2002, 366 (1-2) :1-101
[2]   Reconstructing embedding spaces of coupled dynamical systems from multivariate data [J].
Boccaletti, S ;
Valladares, DL ;
Pecora, LM ;
Geffert, HP ;
Carroll, T .
PHYSICAL REVIEW E, 2002, 65 (03)
[3]   Using reservoir computers to distinguish chaotic signals [J].
Carroll, T. L. .
PHYSICAL REVIEW E, 2018, 98 (05)
[4]   Mapping topological characteristics of dynamical systems into neural networks: A reservoir computing approach [J].
Chen, Xiaolu ;
Weng, Tongfeng ;
Yang, Huijie ;
Gu, Changgui ;
Zhang, Jie ;
Small, Michael .
PHYSICAL REVIEW E, 2020, 102 (03)
[5]   Enhanced P-Type Control: Indirect Adaptive Learning From Set-Point Updates [J].
Chi, Ronghu ;
Li, Huaying ;
Shen, Dong ;
Hou, Zhongsheng ;
Huang, Biao .
IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2023, 68 (03) :1600-1613
[6]   Predicting slow and fast neuronal dynamics with machine learning [J].
Follmann, Rosangela ;
Rosa, Epaminondas, Jr. .
CHAOS, 2019, 29 (11)
[7]   A NEW INTERMITTENCY IN COUPLED DYNAMICAL-SYSTEMS [J].
FUJISAKA, H ;
YAMADA, T .
PROGRESS OF THEORETICAL PHYSICS, 1985, 74 (04) :918-921
[8]   STABILITY THEORY OF SYNCHRONIZED MOTION IN COUPLED-OSCILLATOR SYSTEMS [J].
FUJISAKA, H ;
YAMADA, T .
PROGRESS OF THEORETICAL PHYSICS, 1983, 69 (01) :32-47
[9]   Forecasting chaotic systems with very low connectivity reservoir computers [J].
Griffith, Aaron ;
Pomerance, Andrew ;
Gauthier, Daniel J. .
CHAOS, 2019, 29 (12)