Abstract
We propose a transfer learning for reservoir computing, and verify the effectivity of the proposed methods for the standard inference task of the Lorenz system. Applying the proposed methods to an inference task of fluid physics, we show the inference accuracy is drastically improved compared with the conventional reservoir computing method if available training data size is highly limited.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Inubushi, M., Goto, S.: Inference of the energy dissipation rate of turbulence by machine learning (in preparation)
Inubushi, M., Yoshimura, K.: Reservoir computing beyond memory-nonlinearity trade-off. Sci. Rep. 7(1), 10199 (2017)
Jaeger, H.: The “echo state” approach to analysing and training recurrent neural networks-with an erratum note. Bonn Ger.: Ger. Natl. Res. Cent. Inf. Technol. GMD Tech. Rep. 148(34), 13 (2001)
Lu, Z., Pathak, J., Hunt, B., Girvan, M., Brockett, R., Ott, E.: Reservoir observers: model-free inference of unmeasured variables in chaotic systems. Chaos: Interdisc. J. Nonlinear Sci. 27(4), 041102 (2017)
Silver, D., et al.: Best of NIPS 2005: highlights on the ‘inductive transfer: 10 years later’ workshop (2006)
Weiss, K., Khoshgoftaar, T.M., Wang, D.: A survey of transfer learning. J. Big data 3(1), 9 (2016)
Wu, J.L., Xiao, H., Paterson, E.: Physics-informed machine learning approach for augmenting turbulence models: a comprehensive framework. Phys. Rev. Fluids 3(7), 074602 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Inubushi, M., Goto, S. (2019). Transferring Reservoir Computing: Formulation and Application to Fluid Physics. In: Tetko, I., Kůrková, V., Karpov, P., Theis, F. (eds) Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions. ICANN 2019. Lecture Notes in Computer Science(), vol 11731. Springer, Cham. https://doi.org/10.1007/978-3-030-30493-5_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-30493-5_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-30492-8
Online ISBN: 978-3-030-30493-5
eBook Packages: Computer ScienceComputer Science (R0)