Open Access
Table 1
Hyperparameters used for training the SOM.
| SOM lattice dimensions (wxhxd) | 9×9×1 |
| Number of channels or layers | 1 |
| Training image dimensions | 116 × 116 pixels2, or 82 × 82 pixels2 after rotation |
| Neuron image dimensions | 82 × 82 pixels2 |
| Neighbourhood radius start θ0 | decrease θd | 5 | 0.9 |
| Learning rate start α0 | decrease αd | end αe | 1 | 0.8 | 0.3 |
| Periodic boundary conditions | False |
| Number of training epochs | 25 |
| Initialisation | Zeros |
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.