Fat-U-Net: non-contracting U-Net for free-space optical neural networks
Published in SPIE Photonics West- AI and Optical Data Sciences V, 2024
This paper describes the advantages and disadvantages of adapting the U-Net architecture from a traditional GPU to a 4f free-space optical environment.
Recommended citation: Riad Ibadulla, Constantino C. Reyes-Aldasoro, and Thomas M. Chen "Fat-U-Net: non-contracting U-Net for free-space optical neural networks", Proc. SPIE 12903, AI and Optical Data Sciences V, 1290308 (13 March 2024); https://doi.org/10.1117/12.3008618 https://www.spiedigitallibrary.org/conference-proceedings-of-spie/12903/1290308/Fat-U-Net--non-contracting-U-Net-for-free/10.1117/12.3008618.short#_=_