Cargando…
Single-shot optical neural network
Analog optical and electronic hardware has emerged as a promising alternative to digital electronics to improve the efficiency of deep neural networks (DNNs). However, previous work has been limited in scalability (input vector length K ≈ 100 elements) or has required nonstandard DNN models and retr...
Autores principales: | Bernstein, Liane, Sludds, Alexander, Panuski, Christopher, Trajtenberg-Mills, Sivan, Hamerly, Ryan, Englund, Dirk |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Association for the Advancement of Science
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10284542/ https://www.ncbi.nlm.nih.gov/pubmed/37343096 http://dx.doi.org/10.1126/sciadv.adg7904 |
Ejemplares similares
-
Freely scalable and reconfigurable optical hardware for deep learning
por: Bernstein, Liane, et al.
Publicado: (2021) -
Transferable learning on analog hardware
por: Vadlamani, Sri Krishna, et al.
Publicado: (2023) -
Five-second coherence of a single spin with single-shot readout in silicon carbide
por: Anderson, Christopher P., et al.
Publicado: (2022) -
Event-driven adaptive optical neural network
por: Brückerhoff-Plückelmann, Frank, et al.
Publicado: (2023) -
Data sets and trained neural networks for Cu migration barriers
por: Kimari, Jyri, et al.
Publicado: (2020)