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.

@inproceedings(Griffin++:2023-UCNC,
  author = "David Griffin and Susan Stepney and Ian T. Vidamour",
  title = "Exploring the Robustness of Magnetic Ring Arrays Reservoir Computing with Linear Field Calibration",
  pages = "94-107",    
  doi = "10.1007/978-3-031-34034-5_7",
  crossref = "UCNC-2023"
)

@proceedings(UCNC-2023,
  title = "UCNC 2023, Jacksonville, Florida, USA, March 2023",
  booktitle = "UCNC 2023, Jacksonville, Florida, USA, March 2023",
  series = "LNCS",
  volume = 14003,
  publisher = "Springer",
  year = 2023
)