Fig. 2.
Download original image
Distribution of loss function values of neural networks randomly sampled from tested architectures trained in the task of pseudo-continuum prediction. One hundred random neural networks, with a number of trainable parameters ranging from 200 000 to 300 000, were drawn for each architecture. The training was held in a low-data regime for only 30 epochs.
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.