Potential implementation of reservoir computing models based on magnetic skyrmions
| Autor: | Daniele Pinna, Karin Everschor-Sitte, Matthias Sitte, George I. Bourianoff |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Distributed computing
MathematicsofComputing_NUMERICALANALYSIS FOS: Physical sciences General Physics and Astronomy 02 engineering and technology Memristor 01 natural sciences law.invention law Mesoscale and Nanoscale Physics (cond-mat.mes-hall) 0103 physical sciences 010306 general physics Topology (chemistry) Physics Condensed Matter - Mesoscale and Nanoscale Physics Artificial neural network Hierarchy (mathematics) Skyrmion Reservoir computing Physik (inkl. Astronomie) 021001 nanoscience & nanotechnology lcsh:QC1-999 Recurrent neural network Node (circuits) 0210 nano-technology lcsh:Physics |
| Zdroj: | AIP Advances, Vol 8, Iss 5, Pp 055602-055602-9 (2018) |
| ISSN: | 2158-3226 |
| DOI: | 10.1063/1.5006918 |
| Popis: | Reservoir Computing is a type of recursive neural network commonly used for recognizing and predicting spatio-temporal events relying on a complex hierarchy of nested feedback loops to generate a memory functionality. The Reservoir Computing paradigm does not require any knowledge of the reservoir topology or node weights for training purposes and can therefore utilize naturally existing networks formed by a wide variety of physical processes. Most efforts prior to this have focused on utilizing memristor techniques to implement recursive neural networks. This paper examines the potential of skyrmion fabrics formed in magnets with broken inversion symmetry that may provide an attractive physical instantiation for Reservoir Computing. Comment: 11 pages, 3 figures |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|