Table 4
Model training parameter settings.
| Hyperparameter | Value | Description |
|---|---|---|
| Learning Rate | 0.001 | Initial learning rate for the Adam optimizer, controlling the step size for parameter updates |
| Batch Size | 64 | Number of data samples used in each training update |
| Epochs | 500 | Number of iterations during model training |
| Optimizer | Adam | Optimizer with adaptive learning rate, accelerating the convergence |
| Dropout Rate | 0.5 | 50% of neurons were randomly dropped during training to prevent overfitting |
| Batch Normalization | Yes | Applied in convolutional and LSTM layers to enhance training stability |
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.