Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Shaofu Xu"'
Publikováno v:
Light: Science & Applications, Vol 13, Iss 1, Pp 1-10 (2024)
Abstract Analog feature extraction (AFE) is an appealing strategy for low-latency and efficient cognitive sensing systems since key features are much sparser than the Nyquist-sampled data. However, applying AFE to broadband radio-frequency (RF) scena
Externí odkaz:
https://doaj.org/article/2a499ff70db74c6495fdf73afedebd56
Autor:
Bowen Bai, Qipeng Yang, Haowen Shu, Lin Chang, Fenghe Yang, Bitao Shen, Zihan Tao, Jing Wang, Shaofu Xu, Weiqiang Xie, Weiwen Zou, Weiwei Hu, John E. Bowers, Xingjun Wang
Publikováno v:
Nature Communications, Vol 14, Iss 1, Pp 1-10 (2023)
Optical neural networks face remarkable challenges in high-level integration and on-chip operation. In this work the authors enable optical convolution utilizing time-wavelength plane stretching approach on a microcomb-driven chip-based photonic proc
Externí odkaz:
https://doaj.org/article/c2b40fe948754a689f13bc3bbcbe8d5a
Publikováno v:
Nature Communications, Vol 13, Iss 1, Pp 1-10 (2022)
Convolutional operation is a very efficient way to handle tensor analytics, but it consumes a large quantity of additional memory. Here, the authors demonstrate an integrated photonic tensor processor which directly handles high-order tensors without
Externí odkaz:
https://doaj.org/article/61852ff26665495e87385afe70c0527e
Autor:
Shaofu Xu, Jing Wang, Haowen Shu, Zhike Zhang, Sicheng Yi, Bowen Bai, Xingjun Wang, Jianguo Liu, Weiwen Zou
Publikováno v:
Light: Science & Applications, Vol 10, Iss 1, Pp 1-12 (2021)
An optical coherent chip completes state-of-the-art image reconstruction tasks with 32-bit computer comparable image quality, showing potential in conquering sophisticated deep learning regression tasks.
Externí odkaz:
https://doaj.org/article/d944f037040443c4a5d9ce6602ad1761
Publikováno v:
IEEE Photonics Journal, Vol 13, Iss 1, Pp 1-12 (2021)
We propose a heterogeneous silicon on lithium niobate (Si-LN) modulator which improves the compactness and modulating performance of large-scale photonic integrated circuits. Two types of configurations are employed on the Si-LN wafer for ultra-compa
Externí odkaz:
https://doaj.org/article/b3162c199f8748acb0a289066b015ee1
Publikováno v:
Optics express. 30(23)
Photonics physically promises high-speed and low-consumption computing of matrix multiplication. Nevertheless, conventional approaches are challenging to achieve large throughput, high precision, low power consumption, and high density simultaneously
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::371751d3bf2c6f4e4f5b5a781774abb6
https://pubmed.ncbi.nlm.nih.gov/36366667
https://pubmed.ncbi.nlm.nih.gov/36366667
Publikováno v:
Optics letters. 47(20)
We propose and demonstrate a novel, to the best of our knowledge, joint wireless communication and radar system based on a photonic analog-to-digital converter (PADC), which can receive broadband radio-frequency (RF) signals. Owing to this property,
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cc9953ed99c79bc321d8d7bb359005f1
https://pubmed.ncbi.nlm.nih.gov/36240379
https://pubmed.ncbi.nlm.nih.gov/36240379
Autor:
Bowen Bai, Qipeng Yang, Haowen Shu, Lin Chang, Fenghe Yang, Bitao Shen, Zihan Tao, Jing Wang, Shaofu Xu, Weiqiang Xie, Weiwen Zou, Weiwei Hu, John E. Bowers, Xingjun Wang
Publikováno v:
Nature communications, vol 14, iss 1
The emergence of parallel convolution-operation technology has substantially powered the complexity and functionality of optical neural networks (ONN) by harnessing the dimension of optical wavelength. However, this advanced architecture faces remark
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::590adba14721a982dec866f5fa33e59b
https://pubmed.ncbi.nlm.nih.gov/36604409
https://pubmed.ncbi.nlm.nih.gov/36604409
Publikováno v:
Journal of the Optical Society of America B. 40:1573
The rapid development of fabrication techniques has boosted the resurgence of integrated photonics based on lithium niobate (LN). While thin-film LN is available and has been a promising photonic platform owing to its superior material properties, it
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::afb724436e81bb71ea1d141a7c2ed89d
https://doi.org/10.1364/josab.484460
https://doi.org/10.1364/josab.484460
Publikováno v:
IEEE Photonics Technology Letters. 33:89-92
We propose an optical convolutional neural network (OCNN) architecture for high-speed and energy-efficient deep learning accelerators. The WDM-based optical patching scheme (WDM-OPS) is adopted as the data-feeding structure for its superior energy ef
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8112a23c5dad96280669af24bc94dabf
https://doi.org/10.1109/lpt.2020.3045478
https://doi.org/10.1109/lpt.2020.3045478