Table 1.
Different available training data sets and which machine-learning models used them.
| Data set (size) | Model | ||||
|---|---|---|---|---|---|
| 1 | 2 | 3 | 4 | 5 | |
| S1 (11 057 + 10 311) | ✓ | ✓ | ✓ | ✓ | ✓ |
| S2 (5363) | ✓ | ✓ | ✓ | ✓ | ✓ |
| S3 (2143) | ✓ | ||||
| Real lenses | ✓ | ✓ | ✓* | ✓* | ✓ |
| DESI spirals (∼2300) | ✓ | ✓ | ✓ | ✓ | ✓ |
| DESI mergers (∼250) | ✓ | ✓ | ✓ | ✓ | ✓ |
| DESI rings (∼60) | ✓ | ✓ | ✓ | ✓ | ✓ |
| DESI LRGs (∼2700) | ✓ | ✓ | ✓ | ✓ | |
| DESI others (∼2300) | ✓ | ✓ | ✓ | ||
| S2 random counterpart (4106) | ✓ | ✓ | ✓ | ✓ | |
| EWS random cutouts | ✓ | ✓* | |||
Notes. The size of each data set is shown in brackets, other than the EWS random cutouts and the real lenses, since the different models used different numbers of these. Data sets marked with an asterisk were only used for validation and not training by the model.
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.