Physical reservoir computing: a tutorial
Natural Computing · 2024-12 · 23 (4) · 665-685
DOI: 10.1007/s11047-024-09997-y ↗Kurz gefasst
Fachartikel in der Zeitschrift Natural Computing, online erschienen am 15.11.2024. Verfasst von Susan Stepney. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 94 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: EPSRC.
Abstract (Originalsprache)
This tutorial covers physical reservoir computing from a computer science perspective. It first defines what it means for a physical system to compute, rather than merely evolve under the laws of physics. It describes the underlying computational model, the Echo State Network (ESN), and also some variants designed to make physical implementation easier. It explains why the ESN model is particularly suitable for direct physical implementation. It then discusses the issues around choosing a suitable material substrate, and interfacing the inputs and outputs. It describes how to characterise a physical reservoir in terms of benchmark tasks, and task-independent measures. It covers optimising configuration parameters, exploring the space of potential configurations, and simulating the physical reservoir. It ends with a look at the future of physical reservoir computing as devices get more powerful, and are integrated into larger systems.
Förderung
- EPSRC
Zitieren
APA
Stepney, S. (2024). Physical reservoir computing: a tutorial. Natural Computing, 23(4), 665-685. https://doi.org/10.1007/s11047-024-09997-y
Vancouver
Stepney S. Physical reservoir computing: a tutorial. Natural Computing. 2024;23(4):665-685. doi:10.1007/s11047-024-09997-y
BibTeX
@article{Stepney2024,
author = {Stepney, Susan},
title = {Physical reservoir computing: a tutorial},
journal = {Natural Computing},
year = {2024},
volume = {23},
number = {4},
pages = {665--685},
doi = {10.1007/s11047-024-09997-y}
}
EUVIMED