Open Access

Table 1

Hyperparameters used in RNNs.

Hyperparameter Value Hyperparameter Value
Input features 40 Output layer activation linear
Output size 1 Training loss function MSE
Train/validation ratio (%) 80/20 Training optimizer ADAM
Hidden units 35 Batch rate (%) 5
Hidden layers 1 Dropout rate (%) 0
Hidden layer activation relu Epochs 100

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.