Abstract
An optical neural network architecture is proposed that utilizes parity-time symmetric couplers as its building blocks. Gain–loss contrasts across the array are adjusted as a means to train the network.
© 2022 The Author(s)
PDF Article | Presentation VideoMore Like This
Sri Krishna Vadlamani, Ryan Hamerly, and Dirk Englund
FTh1B.3 Frontiers in Optics (FiO) 2022
Jeng Yi Lee and Pai-Yen Chen
JTu3B.35 CLEO: Applications and Technology (CLEO:A&T) 2022
Martino De Carlo, Francesco De Leonardis, and Vittorio M. N. Passaro
JTu2I.5 CLEO: Applications and Technology (CLEO:A&T) 2021