Abstract
We report a novel robust training regimen for Diffractive Optical Networks that uses gradient based regularization terms in the training objective. Enhanced fault tolerance and noise immunity has been observed with models trained with this method.
© 2021 The Author(s)
PDF Article | Presentation VideoMore Like This
Michael Y-S. Fang, Sasikanth Manipatruni, Casimir Wierzynski, Amir Khosrowshahi, and Ian Young
SF1N.6 CLEO: Science and Innovations (CLEO:S&I) 2019
Tao Fang, Jingwei Li, Biao Zhang, Tongyu Wu, and Xiaowen Dong
JW7A.27 Frontiers in Optics (FiO) 2021
Deniz Mengu, Yifan Zhao, Nezih T. Yardimci, Yair Rivenson, Mona Jarrahi, and Aydogan Ozcan
FM3L.7 CLEO: QELS_Fundamental Science (CLEO:FS) 2021