Open Access
Fig. 3

Download original image
Neural network closed-loop training strategy. The first stage uses the estimate by the NN from open-loop data to compute a residual phase that is used as the input for the second stage. The Zernike coefficients of the residual are used as the ground truth to compute the loss function used to retrain the NN.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.