mean_squared_logarithmic_error.hpp
Go to the documentation of this file.
1 
12 #ifndef MLPACK_METHODS_ANN_LOSS_FUNCTION_MEAN_SQUARED_LOGARITHMIC_ERROR_HPP
13 #define MLPACK_METHODS_ANN_LOSS_FUNCTION_MEAN_SQUARED_LOGARITHMIC_ERROR_HPP
14 
15 #include <mlpack/prereqs.hpp>
16 
17 namespace mlpack {
18 namespace ann {
19 
29 template <
30  typename InputDataType = arma::mat,
31  typename OutputDataType = arma::mat
32 >
34 {
35  public:
40 
47  template<typename InputType, typename TargetType>
48  double Forward(const InputType&& input, const TargetType&& target);
49 
57  template<typename InputType, typename TargetType, typename OutputType>
58  void Backward(const InputType&& input,
59  const TargetType&& target,
60  OutputType&& output);
61 
63  OutputDataType& OutputParameter() const { return outputParameter; }
65  OutputDataType& OutputParameter() { return outputParameter; }
66 
70  template<typename Archive>
71  void serialize(Archive& ar, const unsigned int /* version */);
72 
73  private:
75  OutputDataType outputParameter;
76 }; // class MeanSquaredLogarithmicError
77 
78 } // namespace ann
79 } // namespace mlpack
80 
81 // Include implementation.
82 #include "mean_squared_logarithmic_error_impl.hpp"
83 
84 #endif
strip_type.hpp
Definition: add_to_po.hpp:21
The core includes that mlpack expects; standard C++ includes and Armadillo.
OutputDataType & OutputParameter()
Modify the output parameter.
The mean squared logarithmic error performance function measures the network&#39;s performance according ...
MeanSquaredLogarithmicError()
Create the MeanSquaredLogarithmicError object.
void Backward(const InputType &&input, const TargetType &&target, OutputType &&output)
Ordinary feed backward pass of a neural network.
void serialize(Archive &ar, const unsigned int)
Serialize the layer.
OutputDataType & OutputParameter() const
Get the output parameter.
double Forward(const InputType &&input, const TargetType &&target)
Computes the mean squared logarithmic error function.