Abstract
One of the challenges for reservoir computing is the robustness of the implementation in the face of fabrication error. If a system is too sensitive to fabrication error, then each manufactured reservoir becomes a unique artefact with unique computational properties. Under most circumstances, this is undesirable as it makes reproduction of results, or useful systems, complicated. This paper uses simulation to examine the properties of nano-scale magnetic ring arrays as reservoir computers under parameters corresponding to a wide variety of physically derived parameters, and investigates the effectiveness of linear field calibration to minimise the difference in unexpected behaviour of the systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
This differs from controlled behaviours, which under normal circumstances it is desirable to have as many different types of behaviour as possible.
- 2.
For brevity some details, such as penalty terms on selecting the partition to explore that ensure that all areas of the behaviour space are explored rather than focusing on a infinitesimally small but interesting area, are omitted.
- 3.
These limits are somewhat arbitrary, but approximately reflect the limitations of the current physical implementation with regard to sustained magnetic fields.
References
Bhovad, P., Li, S.: Physical reservoir computing with origami and its application to robotic crawling. Sci. Rep. 11(1), 1–18 (2021)
Bordignon, G., et al.: Analysis of magnetoresistance in arrays of connected Nano-rings. IEEE Trans. Magn. 43(6), 2881–2883 (2007)
Brosamler, G.A.: An almost everywhere central limit theorem. Math. Proc. Cambridge Philos. Soc. 104, 561–574 (1988)
Büsing, L., Schrauwen, B., Legenstein, R.: Connectivity, dynamics, and memory in reservoir computing with binary and analog neurons. Neural Comput. 22(5), 1272–1311 (2010)
Dale, M., et al.: Reservoir computing with thin-film ferromagnetic devices. arXiv preprint arXiv:2101.12700 (2021)
Dale, M., Miller, J.F., Stepney, S., Trefzer, M.: A substrate-independent framework to characterise reservoir computers. Proceed. Royal Soc. A 475, 2226 (2019). https://doi.org/10.1098/rspa.2018.0723
Dawidek, R.W., et al.: Dynamically driven emergence in a nanomagnetic system. Adv. Func. Mater. 31(15), 2008389 (2021)
Franklin, A.: Calibration. Perspect. Sci. 5(1), 31–80 (1997)
Griffin, D.: PyCHARC. https://github.com/dgdguk/pycharc/
Harvey, I.: The microbial genetic algorithm. In: Kampis, G., Karsai, I., Szathmáry, E. (eds.) ECAL 2009. LNCS (LNAI), vol. 5778, pp. 126–133. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21314-4_16
Jaeger, H.: Short term memory in echo state networks. GMD-report 152. In: GMD-German National Research Institute for Computer Science (2002). http://www.faculty.jacobs-university.de/hjaeger/pubs/STMEchoStatesTechRep pdf (2002)
Jaeger, H., Haas, H.: Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304(5667), 78–80 (2004)
Kendall, A., Badrinarayanan, V., Cipolla, R.: Bayesian segNet: model uncertainty in deep convolutional encoder-decoder architectures for scene understanding. In: Kim, T.-K., Stefanos Zafeiriou, G.B., Mikolajczyk, K. (eds.) Proceedings of the British Machine Vision Conference (BMVC), pp. 1-512. BMVA Press (2017). https://doi.org/10.5244/C.31.57
Lehman, J., Stanley, K.O.: Exploiting open-endedness to solve problems through the search for novelty. In: ALife XI, Boston, MA, USA, pp. 329–336. MIT Press (2008)
Schrauwen, B., Verstraeten, D., Van Campenhout, J.: An overview of reservoir computing: theory, applications and implementations. In: Proceedings of the 15th European Symposium on Artificial Neural Networks, pp. 471–482 (2007)
Vansteenkiste, A., Leliaert, J., Dvornik, M., Garcia-Sanchez, F., Van Waeyenberge, B.: The design and verification of mumax3. AIP Adv. 4, 107133 (2014)
Vidamour, I.T., et al.: Quantifying the computational capability of a nanomagnetic reservoir computing platform with emergent magnetisation dynamics. Nanotechnology 33(48), 485203 (2022). https://doi.org/10.1088/1361-6528/ac87b5
Vidamour, I., et al.: Reservoir computing with emergent dynamics in a magnetic metamaterial (2022). https://doi.org/10.48550/ARXIV.2206.04446
Acknowledgments
The authors wish to thank Chalres Vidamour for sharing insight into challenges of the fabrication process of the magnetic ring arrays used in prior work [17]. DG and SS acknowledge funding from the MARCH project, EPSRC grant numbers EP/V006029/1 and EP/V006339/1. IV acknowledges a DTA-funded PhD studentship from EPSRC.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Griffin, D., Stepney, S., Vidamour, I. (2023). Exploring the Robustness of Magnetic Ring Arrays Reservoir Computing with Linear Field Calibration. In: Genova, D., Kari, J. (eds) Unconventional Computation and Natural Computation. UCNC 2023. Lecture Notes in Computer Science, vol 14003. Springer, Cham. https://doi.org/10.1007/978-3-031-34034-5_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-34034-5_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34033-8
Online ISBN: 978-3-031-34034-5
eBook Packages: Computer ScienceComputer Science (R0)