Loss functions define loss values between a model prediction and a given label.
Classes | |
| class | shark::AbstractLoss< LabelT, OutputT > |
| Loss function interface. More... | |
| class | shark::CrossEntropy< LabelType, OutputType > |
| Error measure for classification tasks that can be used as the objective function for training. More... | |
| class | shark::DiscreteLoss |
| flexible loss for classification More... | |
| class | shark::EpsilonHingeLoss |
| Hinge-loss for large margin regression. More... | |
| class | shark::HingeLoss |
| Hinge-loss for large margin classification. More... | |
| class | shark::HuberLoss |
| Huber-loss for for robust regression. More... | |
| class | shark::SquaredEpsilonHingeLoss |
| Hinge-loss for large margin regression using th squared two-norm. More... | |
| class | shark::SquaredHingeLoss |
| Squared Hinge-loss for large margin classification. More... | |
| class | shark::SquaredLoss< OutputType, LabelType > |
| squared loss for regression and classification More... | |
| class | shark::ZeroOneLoss< LabelType, OutputType > |
| 0-1-loss for classification. More... | |