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

Implementation of the variance reduced classification reinforcement layer. More...

#include <vr_class_reward.hpp>

Public Member Functions
	VRClassReward (const double scale=1, const bool sizeAverage=true)
	Create the VRClassReward object. More...
template<typename InputType , typename TargetType >
double	Forward (const InputType &input, const TargetType &target)
	Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. More...
template<typename InputType , typename TargetType , typename OutputType >
void	Backward (const InputType &input, const TargetType &target, OutputType &output)
	Ordinary feed backward pass of a neural network. More...
OutputDataType &	OutputParameter () const
	Get the output parameter.
OutputDataType &	OutputParameter ()
	Modify the output parameter.
OutputDataType &	Delta () const
	Get the delta.
OutputDataType &	Delta ()
	Modify the delta.
template<class LayerType , class... Args>
void	Add (Args... args)
void	Add (LayerTypes<> layer)
std::vector< LayerTypes<> > &	Model ()
	Get the network modules.
bool	SizeAverage () const
	Get the value of parameter sizeAverage.
double	Scale () const
	Get the value of scale parameter.
template<typename Archive >
void	serialize (Archive &, const uint32_t)
	Serialize the layer.

Detailed Description

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

Implementation of the variance reduced classification reinforcement layer.

This layer is meant to be used in combination with the reinforce normal layer (ReinforceNormalLayer), which expects that an reward: (1 for success, 0 otherwise).

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).

Constructor & Destructor Documentation

VRClassReward()

template<typename InputDataType , typename OutputDataType >

mlpack::ann::VRClassReward< InputDataType, OutputDataType >::VRClassReward	(	const double	scale = 1,
		const bool	sizeAverage = true
	)

Create the VRClassReward object.

Parameters

scale	Parameter used to scale the reward.
sizeAverage	Take the average over all batches.

Member Function Documentation

Backward()

template<typename InputDataType , typename OutputDataType >

template<typename InputType , typename TargetType , typename OutputType >

void mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Backward	(	const InputType &	input,
		const TargetType &	target,
		OutputType &	output
	)

Ordinary feed backward pass of a neural network.

The negative log likelihood layer expectes that the input contains log-probabilities for each class. The layer also expects a class index, in the range between 1 and the number of classes, as target when calling the Forward function.

Parameters

input	The propagated input activation.
target	The target vector, that contains the class index in the range between 1 and the number of classes.
output	The calculated error.

Forward()

template<typename InputDataType , typename OutputDataType >

template<typename InputType , typename TargetType >

double mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Forward	(	const InputType &	input,
		const TargetType &	target
	)

Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f.

Parameters

input	Input data that contains the log-probabilities for each class.
target	The target vector, that contains the class index in the range between 1 and the number of classes.

---

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

• src/mlpack/methods/ann/layer/layer_types.hpp
• src/mlpack/methods/ann/layer/vr_class_reward.hpp
• src/mlpack/methods/ann/layer/vr_class_reward_impl.hpp