Abstract
In this short note, the performance of two kinds of physics-guided computing schemes, namely the Hamiltonian Neural Network and the Port-Hamiltonian Neural Network, are discussed through the predicted dynamics of two coupled Duffing oscillators. First, we propose a new error bound which holds for both types of networks. Then, we numerically investigate some alternative activation functions in terms of prediction accuracy. The numerical results show the potential of the approaches when compared to the standard neural networks in the transient regime.
Similar content being viewed by others
References
Strogatz SH (2000) Nonlinear dynamics and chaos: with applications to physics, biology. Westview Press, Chemistry and Engineering
Awrejcewicz J (1991) Bifurcation and chaos in coupled oscillators. World Scientific, Singapore
Deco G, Kringelbach ML, Jirsa VK, Ritter P (2017) The dynamics of resting fluctuations in the brain: metastability and its dynamical cortical core. Sci Rep 7:3095
Qing YM, Ren Y, Lei D, Ma HF, Cui TJ (2022) Strong coupling in two-dimensional materials-based nanostructures: a review. J Opt 24(2):024009
Ceron S, Kimmel MA, Nilles A, Petersen K (2021) Soft robotic oscillators with strain-based coordination. IEEE Robot Autom Lett 6(4):7557–7563
Ikeda Y, Aoyama H, Fujiwara Y, Iyetomi H, Ogimoto K, Souma W, Yoshikawa H (2012) Coupled oscillator model of the business cycle with fluctuating goods markets. Progress Theor Phys Suppl 194:111–121
Hastings A, Abbott KC, Cuddington K, Francis T, Gellner G, Lai Y-C, Morozov A, Petrivskii S, Scranton K, Zeeman ML (2018) Transient phenomena in ecology. Science 361:6406
Simonsen I, Buzna L, Peters K, Bornholdt S, Helbing D (2008) Transient dynamics increasing network vulnerability to cascading failures. Phys Rev Lett 100:218701
Fan H, Wang L, Du Y, Wang Y, Xiao J, Wang X (2022) Learning the dynamics of coupled oscillators from transients. Phys Rev Res 4(1):013137
Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Net 4(2):251–257
Sam Greydanus JY, Dzamba M, Yosinski J (2019) Hamiltonian neural networks. Adv Neural Inform Proc Syst 32:1110–1118
Desai SA, Mattheakis M, Sondak D, Protopapas P, Roberts SJ (2021) Port-hamiltonian neural networks for learning explicit time-dependent dynamical systems. Phys Rev E 104:034312
Choudhary A, Lindner JF, Holliday EG, Miller ST, Sinha S, Ditto WL (2021) Forecasting hamiltonian dynamics without canonical coordinates. Nonlin Dyn 103:1553–1562
Li S, Yang Y (2021) A recurrent neural network framework with an adaptive training strategy for long-time predictive modeling of nonlinear dynamical systems. J Sound Vibr 506:116167
Olmez M, Guzeli C (2015) Exploiting chaos in learning system identification for nonlinear state space models. Neural Process Lett 41:29–41
Ziyin L, Hartwig T, Ueda M (2020) Neural networks fail to learn periodic functions and how to fix it. Adv Neural Inform Proc Syst 33:1583–1594
Mattheakis M, Sondak D, Dogra AS, Protopapas P (2022) Hamiltonian neural networks for solving equations of motion. Phys Rev E 105:065305
Tomasiello S, Loia V, Khaliq A (2021) A granular recurrent neural network for multiple time series prediction. Neural Comput Appl 33:10293–10310
Colace F, Loia V, Tomasiello S (2019) Revising recurrent neural networks from a granular perspective. Appl Soft Comput 82:105535
Choudhary A, Lindner JF, Holliday EG, Miller ST, Sinha S, Ditto WL (2020) Physics-enhanced neural networks learn order and chaos. Phys Rev E 101:062207
Han C-D, Glaz B, Haile M, Lai Y-C (2021) Adaptable Hamiltonian neural networks. Phys Rev Res 3:023156
Zhang H, Fan H, Wang L, Wang X (2021) Learning Hamiltonian dynamics with reservoir computing. Phys Rev E 104:024205
Desai SA, Mattheakis M, Roberts SJ (2021) Variational integrator graph networks for learning energy-conserving dynamical systems. Phys Rev E 104:035310
Md RE, Ul Shougat X, Li T, Mollik E. Perkins (2021) An information theoretic study of a duffing oscillator array reservoir computer. J Comput Nonlinear Dyn 16(8):081004
Goldstein H, Poole C, Safko J (2002) Classical mechanics, 3rd edn. Pearson Addison Wesley, USA
Rajasekar S, Raj SP (1996) The Painlevé property, integrability and chaotic behaviour of a two-coupled Duffing oscillators. Pranama J Phys 47(3):183–198
Hong YP, Pan CT (1992) A lower bound for the smallest singular value. Linear Algebra Appl 172:27–32
Tomasiello S, Pedrycz W, Loia V (2022) Contemporary fuzzy logic: a perspective of fuzzy logic with scilab. Springer, Cham
Virtanen P et al (2020) SciPy 1.0: fundamental algorithms for scientific computing in python. Nat Methods 17:261–272
Loia V, Tomasiello S, Vaccaro A, Gao J (2020) Using local learning with fuzzy transform: application to short term forecasting problems. Fuz Opt Decis Mak 19:13–32
Hastings A (2001) Transient dynamics and persistence of ecological systems. Ecol Lett 4(3):215
Courtney SM, Ungerleider LG, Keil K, Haxby JV (1997) Transient and sustained activity in a distributed neural system for human working memory. Nature 386:608
Acknowledgements
Dr Tomasiello acknowledges funding from the European Social Fund via the IT Academy program and from the Estonian Research Council grant PRG1604.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest. This article does not contain any studies with human participants or animals performed by any of the authors.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Pribõtkin, G., Tomasiello, S. Using Hamiltonian Neural Networks to Model Two Coupled Duffing Oscillators. Neural Process Lett 55, 8163–8180 (2023). https://doi.org/10.1007/s11063-023-11306-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-023-11306-0