Open Access

Fig. 2

image

Download original image

Architecture of POSPEN. The information in the 217 GHz patch is convolved into 8 filters in the first convolutional block. After that, several convolutions are made through four more layers of 32, 64, 128, and 256 filters. The information is then processed through a layer of 128 neurons. Finally, one last neuron gives the output value.

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.