Open Access
Table 3.
Non-structural network hyperparameter values used in training for each dataset.
| Orion | NGC 2264 | Combined | Full 1 kpc | |
|---|---|---|---|---|
| Size | 2394 | 493 | 3586 | 7476 |
| η | 3 × 10−5 | 2 × 10−5 | 4 × 10−5 | 8 × 10−5 |
| α | 0.7 | 0.6 | 0.6 | 0.8 |
| n | 20 | 20 | 20 | 30 |
| ne | 5000 | 5000 | 5000 | 3000 |
Notes. The size of the corresponding training set is put for comparison. η is the learning rate, α the momentum, n the number of neurons in the hidden layer, and ne the number of epochs between two control steps.
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.