Free Access
Table 1.
Parameters used for the first SOM training run.
SOM lattice dimensions (w × h × d) | 10 × 10 × 1 |
Number of channels or layers | 1 |
Representative image dimensions | 67 × 67 pixels2, equivalent to 100 × 100 arcsec2 |
Neighbourhood radius start σ0 | decrease σd | 5 | 0.9 |
Learning rate start α0 | decrease αd | 1 | 0.7 |
Periodic boundary conditions | True |
Stopping condition | AQE improvement per epoch <1% |
Resulting number of training epochs | 23 |
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.