Cargando…
All-optical graph representation learning using integrated diffractive photonic computing units
Photonic neural networks perform brain-inspired computations using photons instead of electrons to achieve substantially improved computing performance. However, existing architectures can only handle data with regular structures but fail to generalize to graph-structured data beyond Euclidean space...
Autores principales: | Yan, Tao, Yang, Rui, Zheng, Ziyang, Lin, Xing, Xiong, Hongkai, Dai, Qionghai |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Association for the Advancement of Science
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9200271/ https://www.ncbi.nlm.nih.gov/pubmed/35704580 http://dx.doi.org/10.1126/sciadv.abn7630 |
Ejemplares similares
-
Photonic unsupervised learning variational autoencoder for high-throughput and low-latency image transmission
por: Chen, Yitong, et al.
Publicado: (2023) -
Ultra-broadband all-optical sampling of optical waveforms
por: Zimin, Dmitry A., et al.
Publicado: (2022) -
All-optical switching based on interacting exciton polaritons in self-assembled perovskite microwires
por: Feng, Jiangang, et al.
Publicado: (2021) -
Simulation of kinematic Kikuchi diffraction patterns from atomistic structures
por: Herron, Adam D., et al.
Publicado: (2018) -
Ultrafast dynamic machine vision with spatiotemporal photonic computing
por: Zhou, Tiankuang, et al.
Publicado: (2023)