Open Access
Table 1.
ANN architecture for training the 21 cm power spectra and cross bias.
| Layers | Description |
|---|---|
| Input | Free parameters |
| Dense 1 | (512 neurons, activation = ‘relu’) |
| Dense 2 | (1024 neurons, activation = ‘relu’) |
| Dense 3 | (1024 neurons, activation = ‘relu’) |
| Dense 4 | (512 neurons, activation = ‘relu’) |
| Dense 5 | (512 neurons, activation = ‘relu’) |
| Dense 6 | (256 neurons, activation = ‘relu’) |
| Dense 7 | (128 neurons, activation = ‘relu’) |
| Dense 8 | (64 neurons, activation = ‘relu’) |
| Dense 9 | (32 neurons, activation = ‘relu’) |
| Dense 10 | (16 neurons, activation = ‘relu’) |
| Output | (values at k bins, activation = ‘linear’) |
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.