Margin ranking loss measures the loss given inputs and a label vector with values of 1 or -1. More...
Public Member Functions | |
| MarginRankingLoss (const double margin=1.0) | |
| Create the MarginRankingLoss object with Hyperparameter margin. More... | |
| template | |
| void | Backward (const InputType &input, const TargetType &target, OutputType &output) |
| Ordinary feed backward pass of a neural network. More... | |
| template | |
| InputType::elem_type | Forward (const InputType &input, const TargetType &target) |
| Computes the Margin Ranking Loss function. More... | |
| double | Margin () const |
| Get the margin parameter. More... | |
| double & | Margin () |
| Modify the margin parameter. More... | |
| OutputDataType & | OutputParameter () const |
| Get the output parameter. More... | |
| OutputDataType & | OutputParameter () |
| Modify the output parameter. More... | |
| template | |
| void | serialize (Archive &ar, const unsigned int) |
| Serialize the layer. More... | |
Detailed Description
template
class mlpack::ann::MarginRankingLoss< InputDataType, OutputDataType >
Margin ranking loss measures the loss given inputs and a label vector with values of 1 or -1.
If the label is 1 then the first input should be ranked higher than the second input at a distance larger than a margin, and vice- versa if the label is -1.
- Template Parameters
-
InputDataType Type of the input data (arma::colvec, arma::mat, arma::sp_mat or arma::cube). OutputDataType Type of the output data (arma::colvec, arma::mat, arma::sp_mat or arma::cube).
Definition at line 35 of file margin_ranking_loss.hpp.
Constructor & Destructor Documentation
◆ MarginRankingLoss()
| MarginRankingLoss | ( | const double | margin = 1.0 | ) |
Create the MarginRankingLoss object with Hyperparameter margin.
Hyperparameter margin defines a minimum distance between correctly ranked samples.
Member Function Documentation
◆ Backward()
| void Backward | ( | const InputType & | input, |
| const TargetType & | target, | ||
| OutputType & | output | ||
| ) |
Ordinary feed backward pass of a neural network.
- Parameters
-
input The propagated concatenated input activation. target The label vector which contains -1 or 1 values. output The calculated error.
◆ Forward()
| InputType::elem_type Forward | ( | const InputType & | input, |
| const TargetType & | target | ||
| ) |
Computes the Margin Ranking Loss function.
- Parameters
-
input Concatenation of the two inputs for evaluating the specified function. target The label vector which contains values of -1 or 1.
◆ Margin() [1/2]
|
inline |
Get the margin parameter.
Definition at line 78 of file margin_ranking_loss.hpp.
◆ Margin() [2/2]
|
inline |
Modify the margin parameter.
Definition at line 80 of file margin_ranking_loss.hpp.
References MarginRankingLoss< InputDataType, OutputDataType >::serialize().
◆ OutputParameter() [1/2]
|
inline |
Get the output parameter.
Definition at line 73 of file margin_ranking_loss.hpp.
◆ OutputParameter() [2/2]
|
inline |
Modify the output parameter.
Definition at line 75 of file margin_ranking_loss.hpp.
◆ serialize()
| void serialize | ( | Archive & | ar, |
| const unsigned | int | ||
| ) |
Serialize the layer.
Referenced by MarginRankingLoss< InputDataType, OutputDataType >::Margin().
The documentation for this class was generated from the following file:
- /home/jenkins-mlpack/mlpack.org/_src/mlpack-3.4.2/src/mlpack/methods/ann/loss_functions/margin_ranking_loss.hpp