Open Access
Table B.1.
Neural network architecture of the emulator.
| Hyperparameter | Value |
|---|---|
| Number of layers | 3 |
| Number of neurons | 64 |
| Batch size | 256 |
| Learning rate | 10−3 |
| Patience value | 30 |
| Maximum epochs | 300 |
| Validation split | 20% |
| Optimizer | Adam |
Notes. The table lists the main hyperparameters adopted in the neural network training, including the number of layers, neurons per layer, and optimisation settings.
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.