Mechanical intelligence via fully reconfigurable elastic neuromorphic metasurfaces
APL Materials · 01.05.2024 · 12 (5)
DOI: 10.1063/5.0201761 ↗Kurz gefasst
Fachartikel in der Zeitschrift APL Materials, online erschienen am 15.05.2024. Verfasst von M. Moghaddaszadeh und 3 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Army Research Office.
Abstract (Originalsprache)
The ability of mechanical systems to perform basic computations has gained traction over recent years, providing an unconventional alternative to digital computing in off grid, low power, and severe environments, which render the majority of electronic components inoperable. However, much of the work in mechanical computing has focused on logic operations via quasi-static prescribed displacements in origami, bistable, and soft deformable matter. Here, we present a first attempt to describe the fundamental framework of an elastic neuromorphic metasurface that performs distinct classification tasks, providing a new set of challenges, given the complex nature of elastic waves with respect to scattering and manipulation. Multiple layers of reconfigurable waveguides are phase-trained via constant weights and trainable activation functions in a manner that enables the resultant wave scattering at the readout location to focus on the correct class within the detection plane. We further demonstrate the neuromorphic system’s reconfigurability in performing two distinct tasks, eliminating the need for costly remanufacturing.
Förderung
- Army Research Office
Zitieren
APA
Moghaddaszadeh, M., Mousa, M., Aref, A., & Nouh, M. (2024). Mechanical intelligence via fully reconfigurable elastic neuromorphic metasurfaces. APL Materials, 12(5). https://doi.org/10.1063/5.0201761
Vancouver
Moghaddaszadeh M, Mousa M, Aref A, Nouh M. Mechanical intelligence via fully reconfigurable elastic neuromorphic metasurfaces. APL Materials. 2024;12(5). doi:10.1063/5.0201761
BibTeX
@article{Moghaddaszadeh2024,
author = {Moghaddaszadeh, M. and Mousa, M. and Aref, A. and Nouh, M.},
title = {Mechanical intelligence via fully reconfigurable elastic neuromorphic metasurfaces},
journal = {APL Materials},
year = {2024},
volume = {12},
number = {5},
doi = {10.1063/5.0201761}
}
EUVIMED