Table 3.
F-score on validation set for the multiclass classification problem for four different models corresponding to different SVM kernels (from top to bottom): linear, radial basis, polynomial of degree two, polynomial of degree three.
Kernel | Optimized C | Optimized γ | F-score |
---|---|---|---|
Linear | 0.0700 | N/A | 0.920 |
RBF | 34.000 | 0.003 | 0.912 |
Poly 2 | 0.0005 | 0.500 | 0.916 |
Poly 3 | 0.0005 | 0.050 | 0.918 |
Notes. Columns: Kernel (first column), hyperparameters optimized in the classification context (second and third columns), and F-score value (last column). Rows: SVM kernels.
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.