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

Public Member Functions
	VRClassReward (const double scale=1, const bool sizeAverage=true)
	Create the VRClassReward object. More...

template<class LayerType , class... Args>
void	Add (Args...args)

void	Add (LayerTypes layer)

template<typename eT >
void	Backward (const arma::Mat< eT > &&input, const arma::Mat< eT > &&target, arma::Mat< eT > &&output)
	Ordinary feed backward pass of a neural network. More...

OutputDataType &	Delta () const
	Get the delta. More...

OutputDataType &	Delta ()
	Modify the delta. More...

bool	Deterministic () const
	Get the value of the deterministic parameter. More...

bool &	Deterministic ()
	Modify the value of the deterministic parameter. More...

template<typename eT >
double	Forward (const arma::Mat< eT > &&input, const arma::Mat< eT > &&target)
	Ordinary feed forward pass of a neural network, evaluating the function f(x) by propagating the activity forward through f. More...

InputDataType &	InputParameter () const
	Get the input parameter. More...

InputDataType &	InputParameter ()
	Modify the input parameter. More...

OutputDataType &	OutputParameter () const
	Get the output parameter. More...

OutputDataType &	OutputParameter ()
	Modify the output parameter. More...

template<typename Archive >
void	Serialize (Archive &, const unsigned int)
	Serialize the layer. More...

Private Attributes
OutputDataType	delta
	Locally-stored delta object. More...

bool	deterministic
	If true dropout and scaling is disabled, see notes above. More...

InputDataType	inputParameter
	Locally-stored input parameter object. More...

std::vector< LayerTypes >	network
	Locally-stored network modules. More...

OutputDataType	outputParameter
	Locally-stored output parameter object. More...

double	reward
	Locally stored reward parameter. More...

const double	scale
	Locally-stored value to scale the reward. More...

const bool	sizeAverage
	If true take the average over all batches. More...

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).

Definition at line 54 of file layer_types.hpp.

Constructor & Destructor Documentation

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

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

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

template<class LayerType , class... Args>

void mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Add ( Args... args )

inline

Definition at line 97 of file vr_class_reward.hpp.

References mlpack::ann::VRClassReward< InputDataType, OutputDataType >::network.

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

void mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Add ( LayerTypes layer )

inline

Definition at line 104 of file vr_class_reward.hpp.

References mlpack::ann::VRClassReward< InputDataType, OutputDataType >::network, and mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Serialize().

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

template<typename eT >

void mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Backward	(	const arma::Mat< eT > &&	input,
		const arma::Mat< eT > &&	target,
		arma::Mat< eT > &&	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.

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

OutputDataType& mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Delta ( ) const

inline

Get the delta.

Definition at line 82 of file vr_class_reward.hpp.

References mlpack::ann::VRClassReward< InputDataType, OutputDataType >::delta.

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

OutputDataType& mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Delta ( )

inline

Modify the delta.

Definition at line 84 of file vr_class_reward.hpp.

References mlpack::ann::VRClassReward< InputDataType, OutputDataType >::delta.

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

bool mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Deterministic ( ) const

inline

Get the value of the deterministic parameter.

Definition at line 87 of file vr_class_reward.hpp.

References mlpack::ann::VRClassReward< InputDataType, OutputDataType >::deterministic.

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

bool& mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Deterministic ( )

inline

Modify the value of the deterministic parameter.

Definition at line 89 of file vr_class_reward.hpp.

References mlpack::ann::VRClassReward< InputDataType, OutputDataType >::deterministic.

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

template<typename eT >

double mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Forward	(	const arma::Mat< eT > &&	input,
		const arma::Mat< eT > &&	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.

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

InputDataType& mlpack::ann::VRClassReward< InputDataType, OutputDataType >::InputParameter ( ) const

inline

Get the input parameter.

Definition at line 72 of file vr_class_reward.hpp.

References mlpack::ann::VRClassReward< InputDataType, OutputDataType >::inputParameter.

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

InputDataType& mlpack::ann::VRClassReward< InputDataType, OutputDataType >::InputParameter ( )

inline

Modify the input parameter.

Definition at line 74 of file vr_class_reward.hpp.

References mlpack::ann::VRClassReward< InputDataType, OutputDataType >::inputParameter.

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

OutputDataType& mlpack::ann::VRClassReward< InputDataType, OutputDataType >::OutputParameter ( ) const

inline

Get the output parameter.

Definition at line 77 of file vr_class_reward.hpp.

References mlpack::ann::VRClassReward< InputDataType, OutputDataType >::outputParameter.

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

OutputDataType& mlpack::ann::VRClassReward< InputDataType, OutputDataType >::OutputParameter ( )

inline

Modify the output parameter.

Definition at line 79 of file vr_class_reward.hpp.

References mlpack::ann::VRClassReward< InputDataType, OutputDataType >::outputParameter.

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

template<typename Archive >

void mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Serialize	(	Archive &	,
		const unsigned	int
	)

Serialize the layer.

Referenced by mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Add().

Member Data Documentation

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

OutputDataType mlpack::ann::VRClassReward< InputDataType, OutputDataType >::delta

private

Locally-stored delta object.

Definition at line 123 of file vr_class_reward.hpp.

Referenced by mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Delta().

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

bool mlpack::ann::VRClassReward< InputDataType, OutputDataType >::deterministic

private

If true dropout and scaling is disabled, see notes above.

Definition at line 132 of file vr_class_reward.hpp.

Referenced by mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Deterministic().

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

InputDataType mlpack::ann::VRClassReward< InputDataType, OutputDataType >::inputParameter

private

Locally-stored input parameter object.

Definition at line 126 of file vr_class_reward.hpp.

Referenced by mlpack::ann::VRClassReward< InputDataType, OutputDataType >::InputParameter().

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

std::vector<LayerTypes> mlpack::ann::VRClassReward< InputDataType, OutputDataType >::network

private

Locally-stored network modules.

Definition at line 135 of file vr_class_reward.hpp.

Referenced by mlpack::ann::VRClassReward< InputDataType, OutputDataType >::Add().

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

OutputDataType mlpack::ann::VRClassReward< InputDataType, OutputDataType >::outputParameter

private

Locally-stored output parameter object.

Definition at line 129 of file vr_class_reward.hpp.

Referenced by mlpack::ann::VRClassReward< InputDataType, OutputDataType >::OutputParameter().

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

double mlpack::ann::VRClassReward< InputDataType, OutputDataType >::reward

private

Locally stored reward parameter.

Definition at line 120 of file vr_class_reward.hpp.

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

const double mlpack::ann::VRClassReward< InputDataType, OutputDataType >::scale

private

Locally-stored value to scale the reward.

Definition at line 114 of file vr_class_reward.hpp.

template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat>

const bool mlpack::ann::VRClassReward< InputDataType, OutputDataType >::sizeAverage

private

If true take the average over all batches.

Definition at line 117 of file vr_class_reward.hpp.

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

Public Member Functions

Private Attributes

Detailed Description

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

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation

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