1
|
Vidamour IT, Ellis MOA, Griffin D, Venkat G, Swindells C, Dawidek RWS, Broomhall TJ, Steinke NJ, Cooper JFK, Maccherozzi F, Dhesi SS, Stepney S, Vasilaki E, Allwood DA, Hayward TJ. Quantifying the computational capability of a nanomagnetic reservoir computing platform with emergent magnetisation dynamics. Nanotechnology 2022; 33:485203. [PMID: 35940063 DOI: 10.1088/1361-6528/ac87b5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/30/2022] [Accepted: 08/08/2022] [Indexed: 06/15/2023]
Abstract
Devices based on arrays of interconnected magnetic nano-rings with emergent magnetization dynamics have recently been proposed for use in reservoir computing applications, but for them to be computationally useful it must be possible to optimise their dynamical responses. Here, we use a phenomenological model to demonstrate that such reservoirs can be optimised for classification tasks by tuning hyperparameters that control the scaling and input-rate of data into the system using rotating magnetic fields. We use task-independent metrics to assess the rings' computational capabilities at each set of these hyperparameters and show how these metrics correlate directly to performance in spoken and written digit recognition tasks. We then show that these metrics, and performance in tasks, can be further improved by expanding the reservoir's output to include multiple, concurrent measures of the ring arrays' magnetic states.
Collapse
Affiliation(s)
- I T Vidamour
- Department of Materials Science and Engineering, University of Sheffield, Sheffield S1 3JD, United Kingdom
| | - M O A Ellis
- Department of Computer Science, University of Sheffield, Sheffield S1 4DP, United Kingdom
| | - D Griffin
- Department of Computer Science, University of York, York YO10 5GH, United Kingdom
| | - G Venkat
- Department of Materials Science and Engineering, University of Sheffield, Sheffield S1 3JD, United Kingdom
| | - C Swindells
- Department of Materials Science and Engineering, University of Sheffield, Sheffield S1 3JD, United Kingdom
| | - R W S Dawidek
- Department of Materials Science and Engineering, University of Sheffield, Sheffield S1 3JD, United Kingdom
| | - T J Broomhall
- Department of Materials Science and Engineering, University of Sheffield, Sheffield S1 3JD, United Kingdom
| | - N J Steinke
- ISIS Neutron and Muon Source, Rutherford Appleton Lab, Didcot, OX11 0QX, United Kingdom
| | - J F K Cooper
- ISIS Neutron and Muon Source, Rutherford Appleton Lab, Didcot, OX11 0QX, United Kingdom
| | - F Maccherozzi
- Diamond Light Source, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0DE, United Kingdom
| | - S S Dhesi
- Diamond Light Source, Harwell Science and Innovation Campus, Didcot, Oxfordshire OX11 0DE, United Kingdom
| | - S Stepney
- Department of Computer Science, University of York, York YO10 5GH, United Kingdom
| | - E Vasilaki
- Department of Computer Science, University of Sheffield, Sheffield S1 4DP, United Kingdom
- Institute of Neuroinformatics, University of Zurich and ETH Zurich, 8057 Zürich, Switzerland
| | - D A Allwood
- Department of Materials Science and Engineering, University of Sheffield, Sheffield S1 3JD, United Kingdom
| | - T J Hayward
- Department of Materials Science and Engineering, University of Sheffield, Sheffield S1 3JD, United Kingdom
| |
Collapse
|