Metasurface-Generated Large and Arbitrary Analog Convolution Kernels for Accelerated Machine Vision DOI
Ruiqi Liang, Shuai Wang, Yiying Dong

et al.

ACS Photonics, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 4, 2024

Language: Английский

Physics and artificial intelligence: illuminating the future of optics and photonics DOI Creative Commons

Md Sadman Sakib Rahman,

Aydogan Özcan

Advanced Photonics, Journal Year: 2024, Volume and Issue: 6(05)

Published: Oct. 31, 2024

The 2024 Nobel Prize in Physics recognized John Hopfield and Geoffrey Hinton for their pioneering work on artificial neural networks, which profoundly impacted the physical sciences, particularly optics photonics. This perspective summarizes laureates' contributions, highlighting physics-based principles inspiration behind development of modern intelligence (AI) also outlining some emerging major advances achieved photonics enabled by AI.

Language: Английский

Citations

4

Teacher-student learning of generative adversarial network-guided diffractive neural networks for visual tracking and imaging DOI Creative Commons
Hang Su,

Yanping He,

Baoli Li

et al.

Advanced Photonics Nexus, Journal Year: 2024, Volume and Issue: 3(06)

Published: Nov. 8, 2024

Efficiently tracking and imaging interested moving targets is crucial across various applications, from autonomous systems to surveillance. However, persistent challenges remain in fields, including environmental intricacies, limitations perceptual technologies, privacy considerations. We present a teacher-student learning model, the generative adversarial network (GAN)-guided diffractive neural (DNN), which performs visual of target. The GAN, as teacher empowers efficient acquisition skill differentiate specific target interest domains imaging. DNN-based student model learns master GAN. process obtaining GAN-guided DNN starts with capturing objects effectively using an event camera high temporal resolution low latency. Then, power GAN utilized generate data position-tracking capability for target, subsequently serving labels training DNN. image during while retaining target's positional information. Our experimental demonstration highlights efficacy expect can significantly enhance

Language: Английский

Citations

0

Metasurface-Generated Large and Arbitrary Analog Convolution Kernels for Accelerated Machine Vision DOI
Ruiqi Liang, Shuai Wang, Yiying Dong

et al.

ACS Photonics, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 4, 2024

Language: Английский

Citations

0