mlpack::ann::SigmoidCrossEntropyError< InputDataType, OutputDataType > Class Template Reference

The SigmoidCrossEntropyError performance function measures the network's performance according to the cross-entropy function between the input and target distributions. More...

#include <sigmoid_cross_entropy_error.hpp>

Public Member Functions
	SigmoidCrossEntropyError ()
	Create the SigmoidCrossEntropyError object.
template<typename PredictionType , typename TargetType >
PredictionType::elem_type	Forward (const PredictionType &prediction, const TargetType &target)
	Computes the Sigmoid CrossEntropy Error functions. More...
template<typename PredictionType , typename TargetType , typename LossType >
void	Backward (const PredictionType &prediction, const TargetType &target, LossType &loss)
	Ordinary feed backward pass of a neural network. More...
OutputDataType &	OutputParameter () const
	Get the output parameter.
OutputDataType &	OutputParameter ()
	Modify the output parameter.
template<typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the layer.

Detailed Description

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
class mlpack::ann::SigmoidCrossEntropyError< InputDataType, OutputDataType >

The SigmoidCrossEntropyError performance function measures the network's performance according to the cross-entropy function between the input and target distributions.

This function calculates the cross entropy given the real values instead of providing the sigmoid activations. The function uses this equivalent formulation: \(max(x, 0) - x * z + \log(1 + e^{-|x|})\) where x = input and z = target.

For more information, see the following paper.

@article{Janocha2017
  title   = {On Loss Functions for Deep Neural Networks in Classification},
  author  = {Katarzyna Janocha, Wojciech Marian Czarnecki},
  url     = {http://arxiv.org/abs/1702.05659},
  journal = {CoRR},
  eprint  = {arXiv:1702.05659},
  year    = {2017}
}

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).

Member Function Documentation

Backward()

template<typename InputDataType , typename OutputDataType >

template<typename PredictionType , typename TargetType , typename LossType >

void mlpack::ann::SigmoidCrossEntropyError< InputDataType, OutputDataType >::Backward ( const PredictionType &  prediction, const TargetType &  target, LossType &  loss  )

inline

Ordinary feed backward pass of a neural network.

Parameters

prediction	Predictions used for evaluating the specified loss function.
target	The target vector.
loss	The calculated error.

Forward()

template<typename InputDataType , typename OutputDataType >

template<typename PredictionType , typename TargetType >

PredictionType::elem_type mlpack::ann::SigmoidCrossEntropyError< InputDataType, OutputDataType >::Forward ( const PredictionType &  prediction, const TargetType &  target  )

inline

Computes the Sigmoid CrossEntropy Error functions.

Parameters

prediction	Predictions used for evaluating the specified loss function.
target	The target vector.

---

The documentation for this class was generated from the following files:

• src/mlpack/methods/ann/loss_functions/sigmoid_cross_entropy_error.hpp
• src/mlpack/methods/ann/loss_functions/sigmoid_cross_entropy_error_impl.hpp