Free Access
Table 1
Validation set accuracy for different machine-learning methods to predict the critical mass.
| Baseline DNN (3 × 128) | 1.67% |
| Linear regression | 30.5% |
| Random forest (10 trees) | 10.5% |
| Random forest (100 trees) | 8.61% |
| Random forest (1000 trees) | 8.18% |
| Random forest (10 000 trees) | 8.11% |
| Support vector regression | 12.5% |
| Gradient boosting | 13.5% |
| Best gradient boosting after random search | 6.82% |
| DNN 2 × 128 | 1.87% |
| DNN 1 × 128 | 13.1% |
| DNN 3 × 64 | 2.31% |
| DNN 3 × 32 | 3.49% |
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.