Abstract
We provide a protocol for training photonic neural networks based on adjoint methods. The gradient of the network with respect to its tunable degrees of freedom is computed by physically backpropagating an optical error signal.
© 2019 The Author(s)
PDF ArticleMore Like This
Momchil Minkov, Tyler W. Hughes, Yu Shi, Ian A. D. Williamson, and Shanhui Fan
FW1C.3 Frontiers in Optics (FiO) 2018
Sunil Pai, Tyler W. Hughes, Taewon Park, Ben Bartlett, Ian Williamson, Momchil Minkov, Maziyar Milanizadeh, Nathnael Abebe, Francesco Morichetti, Andrea Melloni, Olav Solgaard, Shanhui Fan, and David A. B. Miller
STh5G.2 CLEO: Science and Innovations (CLEO:S&I) 2022
Logan G. Wright, Tatsuhiro Onodera, Martin M. Stein, Tianyu Wang, Darren T. Schachter, Zoey Hu, and Peter L. McMahon
NTh1A.6 Nonlinear Optics (NLO) 2021