12 #ifndef MLPACK_METHODS_ANN_LOSS_FUNCTION_MEAN_SQUARED_ERROR_HPP 13 #define MLPACK_METHODS_ANN_LOSS_FUNCTION_MEAN_SQUARED_ERROR_HPP 31 typename InputDataType = arma::mat,
32 typename OutputDataType = arma::mat
49 template<
typename PredictionType,
typename TargetType>
50 typename PredictionType::elem_type
Forward(
const PredictionType& prediction,
51 const TargetType& target);
61 template<
typename PredictionType,
typename TargetType,
typename LossType>
62 void Backward(
const PredictionType& prediction,
63 const TargetType& target,
74 template<
typename Archive>
75 void serialize(Archive& ar,
const uint32_t );
79 OutputDataType outputParameter;
Linear algebra utility functions, generally performed on matrices or vectors.
Definition: cv.hpp:1
void Backward(const PredictionType &prediction, const TargetType &target, LossType &loss)
Ordinary feed backward pass of a neural network.
Definition: mean_squared_error_impl.hpp:39
The core includes that mlpack expects; standard C++ includes and Armadillo.
void serialize(Archive &ar, const uint32_t)
Serialize the layer.
Definition: mean_squared_error_impl.hpp:49
OutputDataType & OutputParameter()
Modify the output parameter.
Definition: mean_squared_error.hpp:69
OutputDataType & OutputParameter() const
Get the output parameter.
Definition: mean_squared_error.hpp:67
The mean squared error performance function measures the network's performance according to the mean ...
Definition: mean_squared_error.hpp:34
MeanSquaredError()
Create the MeanSquaredError object.
Definition: mean_squared_error_impl.hpp:22
PredictionType::elem_type Forward(const PredictionType &prediction, const TargetType &target)
Computes the mean squared error function.
Definition: mean_squared_error_impl.hpp:30