Experimental demonstration of coupled learning in elastic networks
Physical Review Applied · 20.08.2024 · 22 (2)
DOI: 10.1103/physrevapplied.22.024053 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physical Review Applied, online erschienen am 20.08.2024. Verfasst von Lauren E. Altman und 3 weiteren Autor:innen. Die Arbeit wurde bisher 32-mal zitiert (Crossref) und nennt 32 Literaturangaben. Gefördert von: NSF, U.S. Department of Energy, Basic Energy Sciences.
Abstract (Originalsprache)
Coupled learning is a contrastive scheme for tuning the properties of individual elements within a network in order to achieve desired functionality of the system. It takes advantage of physics both to learn using local rules and to"compute"the output response to input data, thus enabling the system to perform decentralized computation without the need for a processor or external memory. We demonstrate a proof-of-concept mechanical network that can learn simple tasks such as self-symmetrizing via iterative tuning of individual spring rest lengths. These mechanical networks could feasibly be scaled and automated to solve increasingly complex tasks, hinting at a new class of smart metamaterials.
Förderung
- NSF
- U.S. Department of Energy
- Basic Energy Sciences
- Division of Materials Sciences and Engineering
- Simons Foundation
- EPSRC
Zitieren
APA
Altman, L. E., Stern, M., Liu, A. J., & Durian, D. J. (2024). Experimental demonstration of coupled learning in elastic networks. Physical Review Applied, 22(2). https://doi.org/10.1103/physrevapplied.22.024053
Vancouver
Altman LE, Stern M, Liu AJ, Durian DJ. Experimental demonstration of coupled learning in elastic networks. Physical Review Applied. 2024;22(2). doi:10.1103/physrevapplied.22.024053
BibTeX
@article{Altman2024,
author = {Altman, Lauren E. and Stern, Menachem and Liu, Andrea J. and Durian, Douglas J.},
title = {Experimental demonstration of coupled learning in elastic networks},
journal = {Physical Review Applied},
year = {2024},
volume = {22},
number = {2},
doi = {10.1103/physrevapplied.22.024053}
}
EUVIMED