2000 character limit reached
Learning unidirectional coupling using echo-state network (2303.13562v1)
Published 23 Mar 2023 in cs.LG
Abstract: Reservoir Computing has found many potential applications in the field of complex dynamics. In this article, we exploit the exceptional capability of the echo-state network (ESN) model to make it learn a unidirectional coupling scheme from only a few time series data of the system. We show that, once trained with a few example dynamics of a drive-response system, the machine is able to predict the response system's dynamics for any driver signal with the same coupling. Only a few time series data of an $A-B$ type drive-response system in training is sufficient for the ESN to learn the coupling scheme. After training even if we replace drive system $A$ with a different system $C$, the ESN can reproduce the dynamics of response system $B$ using the dynamics of new drive system $C$ only.
- J. Meiyazhagan, S. Sudharsan, and M. Senthilvelan, Model-free prediction of emergence of extreme events in a parametrically driven nonlinear dynamical system by deep learning, The European Physical Journal B 94, 1 (2021).
- C. Gallicchio and A. Micheli, Echo state property of deep reservoir computing networks, Cognitive Computation 9, 337 (2017).
- K. Nakajima, Physical reservoir computing—an introductory perspective, Japanese Journal of Applied Physics 59, 060501 (2020).
- H. Jaeger, The “echo state” approach to analysing and training recurrent neural networks-with an erratum note, Bonn, Germany: German National Research Center for Information Technology GMD Technical Report 148, 13 (2001).
- W. Maass, T. Natschläger, and H. Markram, Real-time computing without stable states: A new framework for neural computation based on perturbations, Neural computation 14, 2531 (2002).
- M. Lukoševičius and H. Jaeger, Reservoir computing approaches to recurrent neural network training, Computer Science Review 3, 127 (2009).
- M. Lukoševičius, H. Jaeger, and B. Schrauwen, Reservoir computing trends, KI-Künstliche Intelligenz 26, 365 (2012).
- Z. Lu, B. R. Hunt, and E. Ott, Attractor reconstruction by machine learning, Chaos: An Interdisciplinary Journal of Nonlinear Science 28, 061104 (2018).
- A. Röhm, D. J. Gauthier, and I. Fischer, Model-free inference of unseen attractors: Reconstructing phase space features from a single noisy trajectory using reservoir computing, Chaos: An Interdisciplinary Journal of Nonlinear Science 31, 103127 (2021).
- J. C. Coulombe, M. C. York, and J. Sylvestre, Computing with networks of nonlinear mechanical oscillators, PloS one 12, e0178663 (2017).
- J. Choi and P. Kim, Critical neuromorphic computing based on explosive synchronization, Chaos: An Interdisciplinary Journal of Nonlinear Science 29, 043110 (2019).
- S. Mandal and M. D. Shrimali, Achieving criticality for reservoir computing using environment-induced explosive death, Chaos: An Interdisciplinary Journal of Nonlinear Science 31, 031101 (2021).
- J. Jensen and G. Tufte, Reservoir computing with a chaotic circuit, in Proceedings of the European Conference on Artificial Life 2017 (MIT Press, 2017).
- S. Mandal, S. Sinha, and M. D. Shrimali, Machine-learning potential of a single pendulum, Physical Review E 105, 054203 (2022).
- D. G. Aronson, G. B. Ermentrout, and N. Kopell, Amplitude response of coupled oscillators, Physica D: Nonlinear Phenomena 41, 403 (1990).
- K. Bar-Eli, On the stability of coupled chemical oscillators, Physica D: Nonlinear Phenomena 14, 242 (1985).
- S. H. Strogatz and I. Stewart, Coupled oscillators and biological synchronization, Scientific American 269, 102 (1993).
- E. Steur, I. Tyukin, and H. Nijmeijer, Semi-passivity and synchronization of diffusively coupled neuronal oscillators, Physica D: Nonlinear Phenomena 238, 2119 (2009).
- A. Sharma and M. D. Shrimali, Amplitude death with mean-field diffusion, Physical Review E 85, 057204 (2012).
- D. M. Abrams and S. H. Strogatz, Chimera states for coupled oscillators, Physical review letters 93, 174102 (2004).
- S. Kim, S. H. Park, and C. Ryu, Multistability in coupled oscillator systems with time delay, Physical review letters 79, 2911 (1997).
- L. M. Pecora and T. L. Carroll, Driving systems with chaotic signals, Physical review A 44, 2374 (1991).
- A. Uchida, R. McAllister, and R. Roy, Consistency of nonlinear system response to complex drive signals, Physical review letters 93, 244102 (2004).
- M. Agrawal, A. Prasad, and R. Ramaswamy, Driving-induced bistability in coupled chaotic attractors, Physical Review E 87, 042909 (2013).
- L. M. Pecora and T. L. Carroll, Synchronization in chaotic systems, Physical review letters 64, 821 (1990).
- C. Tresser, P. A. Worfolk, and H. Bass, Master-slave synchronization from the point of view of global dynamics, Chaos: An Interdisciplinary Journal of Nonlinear Science 5, 693 (1995).
- J. Mei, M. Jiang, and J. Wang, Finite-time structure identification and synchronization of drive-response systems with uncertain parameter, Communications in Nonlinear Science and Numerical Simulation 18, 999 (2013).
- K.-Z. Li, M.-C. Zhao, and X.-C. Fu, Projective synchronization of driving–response systems and its application to secure communication, IEEE Transactions on Circuits and Systems I: Regular Papers 56, 2280 (2009).
- A. E. Botha and M. R. Kolahchi, Analysis of chimera states as drive-response systems, Scientific Reports 8, 1 (2018).
- R. Q. Quiroga, J. Arnhold, and P. Grassberger, Learning driver-response relationships from synchronization patterns, Physical Review E 61, 5142 (2000).
- J. Yperman and T. Becker, Bayesian optimization of hyper-parameters in reservoir computing, arXiv preprint arXiv:1611.05193 (2016).
- A. Griffith, A. Pomerance, and D. J. Gauthier, Forecasting chaotic systems with very low connectivity reservoir computers, Chaos: An Interdisciplinary Journal of Nonlinear Science 29, 123108 (2019).