Scheme of the implemented deep learning protocol. (IMAGE)
Caption
Scheme of the implemented deep learning protocol. A limited number of quantum probe states are fed into the sensor treated as a black box. A grid of measurement results is collected to train a neural network, which learns the posterior probability distribution associated with the single-measurement Bayesian update. Such distribution is used to define the reward of the RL agent that sets the control phases on the black-box device.
Credit
Cimini et al., doi 10.1117/1.AP.5.1.016005.
Usage Restrictions
NONE
License
Original content