mlpack 3.4.2
hinge_embedding_loss.hpp
Go to the documentation of this file.
1
15#ifndef MLPACK_METHODS_ANN_LOSS_FUNCTION_HINGE_EMBEDDING_LOSS_HPP
16#define MLPACK_METHODS_ANN_LOSS_FUNCTION_HINGE_EMBEDDING_LOSS_HPP
17
18#include <mlpack/prereqs.hpp>
19
20namespace mlpack {
21namespace ann {
22
32template <
33 typename InputDataType = arma::mat,
34 typename OutputDataType = arma::mat
35>
37{
38 public:
43
50 template<typename InputType, typename TargetType>
51 typename InputType::elem_type Forward(const InputType& input,
52 const TargetType& target);
53
61 template<typename InputType, typename TargetType, typename OutputType>
62 void Backward(const InputType& input,
63 const TargetType& target,
64 OutputType& output);
65
67 OutputDataType& OutputParameter() const { return outputParameter; }
69 OutputDataType& OutputParameter() { return outputParameter; }
70
74 template<typename Archive>
75 void serialize(Archive& ar, const unsigned int /* version */);
76
77 private:
79 OutputDataType outputParameter;
80}; // class HingeEmbeddingLoss
81
82} // namespace ann
83} // namespace mlpack
84
85// include implementation
86#include "hinge_embedding_loss_impl.hpp"
87
88#endif
The Hinge Embedding loss function is often used to compute the loss between y_true and y_pred.
HingeEmbeddingLoss()
Create the Hinge Embedding object.
OutputDataType & OutputParameter() const
Get the output parameter.
void Backward(const InputType &input, const TargetType &target, OutputType &output)
Ordinary feed backward pass of a neural network.
InputType::elem_type Forward(const InputType &input, const TargetType &target)
Computes the Hinge Embedding loss function.
OutputDataType & OutputParameter()
Modify the output parameter.
void serialize(Archive &ar, const unsigned int)
Serialize the loss function.
Linear algebra utility functions, generally performed on matrices or vectors.
Definition: cv.hpp:1
The core includes that mlpack expects; standard C++ includes and Armadillo.