absolute loss More...
#include <shark/ObjectiveFunctions/Loss/AbsoluteLoss.h>
Inheritance diagram for shark::AbsoluteLoss< VectorType >:
Public Member Functions | |
| AbsoluteLoss () | |
| constructor More... | |
| std::string | name () const |
| From INameable: return the class name. More... | |
| double | eval (BatchLabelType const &labels, BatchOutputType const &predictions) const |
| Public Member Functions inherited from shark::AbstractLoss< VectorType, VectorType > | |
| AbstractLoss () | |
| virtual double | eval (ConstLabelReference target, ConstOutputReference prediction) const |
| evaluate the loss for a target and a prediction More... | |
| double | eval (Data< LabelType > const &targets, Data< OutputType > const &predictions) const |
| virtual double | evalDerivative (ConstLabelReference target, ConstOutputReference prediction, OutputType &gradient) const |
| evaluate the loss and its derivative for a target and a prediction More... | |
| virtual double | evalDerivative (ConstLabelReference target, ConstOutputReference prediction, OutputType &gradient, MatrixType &hessian) const |
| evaluate the loss and its first and second derivative for a target and a prediction More... | |
| virtual double | evalDerivative (BatchLabelType const &target, BatchOutputType const &prediction, BatchOutputType &gradient) const |
| evaluate the loss and the derivative w.r.t. the prediction More... | |
| double | operator() (LabelType const &target, OutputType const &prediction) const |
| evaluate the loss for a target and a prediction More... | |
| double | operator() (BatchLabelType const &target, BatchOutputType const &prediction) const |
| Public Member Functions inherited from shark::AbstractCost< VectorType, VectorType > | |
| virtual | ~AbstractCost () |
| const Features & | features () const |
| virtual void | updateFeatures () |
| bool | hasFirstDerivative () const |
| returns true when the first parameter derivative is implemented More... | |
| bool | isLossFunction () const |
| returns true when the cost function is in fact a loss function More... | |
| double | operator() (Data< LabelType > const &targets, Data< OutputType > const &predictions) const |
| Public Member Functions inherited from shark::INameable | |
| virtual | ~INameable () |
Additional Inherited Members | |
| Protected Attributes inherited from shark::AbstractCost< VectorType, VectorType > | |
| Features | m_features |
Detailed Description
template<class VectorType = RealVector>
class shark::AbsoluteLoss< VectorType >
absolute loss
The absolute loss is usually defined in a single dimension as the absolute value of the difference between labels and predictions. Here we generalize to multiple dimensions by returning the norm.
Definition at line 50 of file AbsoluteLoss.h.
Member Typedef Documentation
◆ BatchLabelType
| typedef base_type::BatchLabelType shark::AbsoluteLoss< VectorType >::BatchLabelType |
Definition at line 54 of file AbsoluteLoss.h.
◆ BatchOutputType
| typedef base_type::BatchOutputType shark::AbsoluteLoss< VectorType >::BatchOutputType |
Definition at line 55 of file AbsoluteLoss.h.
Constructor & Destructor Documentation
◆ AbsoluteLoss()
|
inline |
constructor
Definition at line 58 of file AbsoluteLoss.h.
Member Function Documentation
◆ eval()
|
inlinevirtual |
evaluate the loss \( \| labels - predictions \| \), which is a slight generalization of the absolute value of the difference.
Implements shark::AbstractLoss< VectorType, VectorType >.
Definition at line 71 of file AbsoluteLoss.h.
References SIZE_CHECK.
◆ name()
|
inlinevirtual |
From INameable: return the class name.
Reimplemented from shark::INameable.
Definition at line 63 of file AbsoluteLoss.h.
References shark::AbstractLoss< VectorType, VectorType >::eval().
The documentation for this class was generated from the following file:
- include/shark/ObjectiveFunctions/Loss/AbsoluteLoss.h