mlpack::ann Namespace Reference

Artificial Neural Network. More...

Namespaces
	augmented

Classes
class	Add
	Implementation of the Add module class. More...
class	AddMerge
	Implementation of the AddMerge module class. More...
class	AddVisitor
	AddVisitor exposes the Add() method of the given module. More...
class	AlphaDropout
	The alpha - dropout layer is a regularizer that randomly with probability 'ratio' sets input values to alphaDash. More...
class	AtrousConvolution
	Implementation of the Atrous Convolution class. More...
class	BackwardVisitor
	BackwardVisitor executes the Backward() function given the input, error and delta parameter. More...
class	BaseLayer
	Implementation of the base layer. More...
class	BatchNorm
	Declaration of the Batch Normalization layer class. More...
class	BernoulliDistribution
	Multiple independent Bernoulli distributions. More...
class	BilinearInterpolation
	Definition and Implementation of the Bilinear Interpolation Layer. More...
class	BinaryRBM
	For more information, see the following paper: More...
class	BRNN
	Implementation of a standard bidirectional recurrent neural network container. More...
class	Concat
	Implementation of the Concat class. More...
class	Concatenate
	Implementation of the Concatenate module class. More...
class	ConcatPerformance
	Implementation of the concat performance class. More...
class	Constant
	Implementation of the constant layer. More...
class	ConstInitialization
	This class is used to initialize weight matrix with constant values. More...
class	Convolution
	Implementation of the Convolution class. More...
class	CopyVisitor
	This visitor is to support copy constructor for neural network module. More...
class	CReLU
	A concatenated ReLU has two outputs, one ReLU and one negative ReLU, concatenated together. More...
class	CrossEntropyError
	The cross-entropy performance function measures the network's performance according to the cross-entropy between the input and target distributions. More...
class	DeleteVisitor
	DeleteVisitor executes the destructor of the instantiated object. More...
class	DeltaVisitor
	DeltaVisitor exposes the delta parameter of the given module. More...
class	DeterministicSetVisitor
	DeterministicSetVisitor set the deterministic parameter given the deterministic value. More...
class	DiceLoss
	The dice loss performance function measures the network's performance according to the dice coefficient between the input and target distributions. More...
class	DropConnect
	The DropConnect layer is a regularizer that randomly with probability ratio sets the connection values to zero and scales the remaining elements by factor 1 /(1 - ratio). More...
class	Dropout
	The dropout layer is a regularizer that randomly with probability 'ratio' sets input values to zero and scales the remaining elements by factor 1 / (1 - ratio) rather than during test time so as to keep the expected sum same. More...
class	EarthMoverDistance
	The earth mover distance function measures the network's performance according to the Kantorovich-Rubinstein duality approximation. More...
class	ELU
	The ELU activation function, defined by. More...
class	FastLSTM
	An implementation of a faster version of the Fast LSTM network layer. More...
class	FFN
	Implementation of a standard feed forward network. More...
class	FFTConvolution
	Computes the two-dimensional convolution through fft. More...
class	FlexibleReLU
	The FlexibleReLU activation function, defined by. More...
class	ForwardVisitor
	ForwardVisitor executes the Forward() function given the input and output parameter. More...
class	FullConvolution
class	GaussianInitialization
	This class is used to initialize weigth matrix with a gaussian. More...
class	Glimpse
	The glimpse layer returns a retina-like representation (down-scaled cropped images) of increasing scale around a given location in a given image. More...
class	GlorotInitializationType
	This class is used to initialize the weight matrix with the Glorot Initialization method. More...
class	GradientSetVisitor
	GradientSetVisitor update the gradient parameter given the gradient set. More...
class	GradientUpdateVisitor
	GradientUpdateVisitor update the gradient parameter given the gradient set. More...
class	GradientVisitor
	SearchModeVisitor executes the Gradient() method of the given module using the input and delta parameter. More...
class	GradientZeroVisitor
class	GRU
	An implementation of a gru network layer. More...
class	HardSigmoidFunction
	The hard sigmoid function, defined by. More...
class	HardTanH
	The Hard Tanh activation function, defined by. More...
class	HeInitialization
	This class is used to initialize weight matrix with the He initialization rule given by He et. More...
class	IdentityFunction
	The identity function, defined by. More...
class	InitTraits
	This is a template class that can provide information about various initialization methods. More...
class	InitTraits< KathirvalavakumarSubavathiInitialization >
	Initialization traits of the kathirvalavakumar subavath initialization rule. More...
class	InitTraits< NguyenWidrowInitialization >
	Initialization traits of the Nguyen-Widrow initialization rule. More...
class	Join
	Implementation of the Join module class. More...
class	KathirvalavakumarSubavathiInitialization
	This class is used to initialize the weight matrix with the method proposed by T. More...
class	KLDivergence
	The Kullback–Leibler divergence is often used for continuous distributions (direct regression). More...
class	LayerNorm
	Declaration of the Layer Normalization class. More...
class	LayerTraits
	This is a template class that can provide information about various layers. More...
class	LeakyReLU
	The LeakyReLU activation function, defined by. More...
class	LecunNormalInitialization
	This class is used to initialize weight matrix with the Lecun Normalization initialization rule. More...
class	Linear
	Implementation of the Linear layer class. More...
class	LinearNoBias
	Implementation of the LinearNoBias class. More...
class	LoadOutputParameterVisitor
	LoadOutputParameterVisitor restores the output parameter using the given parameter set. More...
class	LogisticFunction
	The logistic function, defined by. More...
class	LogSoftMax
	Implementation of the log softmax layer. More...
class	Lookup
	Implementation of the Lookup class. More...
class	LossVisitor
	LossVisitor exposes the Loss() method of the given module. More...
class	LSTM
	Implementation of the LSTM module class. More...
class	MaxPooling
	Implementation of the MaxPooling layer. More...
class	MaxPoolingRule
class	MeanPooling
	Implementation of the MeanPooling. More...
class	MeanPoolingRule
class	MeanSquaredError
	The mean squared error performance function measures the network's performance according to the mean of squared errors. More...
class	MultiplyConstant
	Implementation of the multiply constant layer. More...
class	MultiplyMerge
	Implementation of the MultiplyMerge module class. More...
class	NaiveConvolution
	Computes the two-dimensional convolution. More...
class	NegativeLogLikelihood
	Implementation of the negative log likelihood layer. More...
class	NetworkInitialization
	This class is used to initialize the network with the given initialization rule. More...
class	NguyenWidrowInitialization
	This class is used to initialize the weight matrix with the Nguyen-Widrow method. More...
class	OivsInitialization
	This class is used to initialize the weight matrix with the oivs method. More...
class	OrthogonalInitialization
	This class is used to initialize the weight matrix with the orthogonal matrix initialization. More...
class	OutputHeightVisitor
	OutputHeightVisitor exposes the OutputHeight() method of the given module. More...
class	OutputParameterVisitor
	OutputParameterVisitor exposes the output parameter of the given module. More...
class	OutputWidthVisitor
	OutputWidthVisitor exposes the OutputWidth() method of the given module. More...
class	ParametersSetVisitor
	ParametersSetVisitor update the parameters set using the given matrix. More...
class	ParametersVisitor
	ParametersVisitor exposes the parameters set of the given module and stores the parameters set into the given matrix. More...
class	PReLU
	The PReLU activation function, defined by (where alpha is trainable) More...
class	RandomInitialization
	This class is used to initialize randomly the weight matrix. More...
class	RBM
	The implementation of the RBM module. More...
class	ReconstructionLoss
	The reconstruction loss performance function measures the network's performance equal to the negative log probability of the target with the input distribution. More...
class	RectifierFunction
	The rectifier function, defined by. More...
class	Recurrent
	Implementation of the RecurrentLayer class. More...
class	RecurrentAttention
	This class implements the Recurrent Model for Visual Attention, using a variety of possible layer implementations. More...
class	ReinforceNormal
	Implementation of the reinforce normal layer. More...
class	Reparametrization
	Implementation of the Reparametrization layer class. More...
class	ResetCellVisitor
	ResetCellVisitor executes the ResetCell() function. More...
class	ResetVisitor
	ResetVisitor executes the Reset() function. More...
class	RewardSetVisitor
	RewardSetVisitor set the reward parameter given the reward value. More...
class	RNN
	Implementation of a standard recurrent neural network container. More...
class	RunSetVisitor
	RunSetVisitor set the run parameter given the run value. More...
class	SaveOutputParameterVisitor
	SaveOutputParameterVisitor saves the output parameter into the given parameter set. More...
class	Select
	The select module selects the specified column from a given input matrix. More...
class	Sequential
	Implementation of the Sequential class. More...
class	SetInputHeightVisitor
	SetInputHeightVisitor updates the input height parameter with the given input height. More...
class	SetInputWidthVisitor
	SetInputWidthVisitor updates the input width parameter with the given input width. More...
class	SigmoidCrossEntropyError
	The SigmoidCrossEntropyError performance function measures the network's performance according to the cross-entropy function between the input and target distributions. More...
class	SoftplusFunction
	The softplus function, defined by. More...
class	SoftsignFunction
	The softsign function, defined by. More...
class	SpikeSlabRBM
	For more information, see the following paper: More...
class	Subview
	Implementation of the subview layer. More...
class	SVDConvolution
	Computes the two-dimensional convolution using singular value decomposition. More...
class	SwishFunction
	The swish function, defined by. More...
class	TanhFunction
	The tanh function, defined by. More...
class	TransposedConvolution
	Implementation of the Transposed Convolution class. More...
class	ValidConvolution
class	VRClassReward
	Implementation of the variance reduced classification reinforcement layer. More...
class	WeightSetVisitor
	WeightSetVisitor update the module parameters given the parameters set. More...
class	WeightSizeVisitor
	WeightSizeVisitor returns the number of weights of the given module. More...

Typedefs
template<class ActivationFunction = LogisticFunction, typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
using	CustomLayer = BaseLayer< ActivationFunction, InputDataType, OutputDataType >
	Standard Sigmoid layer. More...
template<typename MatType = arma::mat>
using	Embedding = Lookup< MatType, MatType >
using	GlorotInitialization = GlorotInitializationType< false >
	GlorotInitialization uses uniform distribution. More...
template<class ActivationFunction = HardSigmoidFunction, typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
using	HardSigmoidLayer = BaseLayer< ActivationFunction, InputDataType, OutputDataType >
	Standard HardSigmoid-Layer using the HardSigmoid activation function. More...
template<class ActivationFunction = IdentityFunction, typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
using	IdentityLayer = BaseLayer< ActivationFunction, InputDataType, OutputDataType >
	Standard Identity-Layer using the identity activation function. More...
template<typename... CustomLayers>
using	LayerTypes = boost::variant< Add< arma::mat, arma::mat > *, AddMerge< arma::mat, arma::mat > *, AtrousConvolution< NaiveConvolution< ValidConvolution >, NaiveConvolution< FullConvolution >, NaiveConvolution< ValidConvolution >, arma::mat, arma::mat > *, BaseLayer< LogisticFunction, arma::mat, arma::mat > *, BaseLayer< IdentityFunction, arma::mat, arma::mat > *, BaseLayer< TanhFunction, arma::mat, arma::mat > *, BaseLayer< RectifierFunction, arma::mat, arma::mat > *, BaseLayer< SoftplusFunction, arma::mat, arma::mat > *, BatchNorm< arma::mat, arma::mat > *, BilinearInterpolation< arma::mat, arma::mat > *, Concat< arma::mat, arma::mat > *, Concatenate< arma::mat, arma::mat > *, ConcatPerformance< NegativeLogLikelihood< arma::mat, arma::mat >, arma::mat, arma::mat > *, Constant< arma::mat, arma::mat > *, Convolution< NaiveConvolution< ValidConvolution >, NaiveConvolution< FullConvolution >, NaiveConvolution< ValidConvolution >, arma::mat, arma::mat > *, TransposedConvolution< NaiveConvolution< ValidConvolution >, NaiveConvolution< FullConvolution >, NaiveConvolution< ValidConvolution >, arma::mat, arma::mat > *, DropConnect< arma::mat, arma::mat > *, Dropout< arma::mat, arma::mat > *, AlphaDropout< arma::mat, arma::mat > *, ELU< arma::mat, arma::mat > *, FlexibleReLU< arma::mat, arma::mat > *, Glimpse< arma::mat, arma::mat > *, HardTanH< arma::mat, arma::mat > *, Join< arma::mat, arma::mat > *, LayerNorm< arma::mat, arma::mat > *, LeakyReLU< arma::mat, arma::mat > *, CReLU< arma::mat, arma::mat > *, Linear< arma::mat, arma::mat > *, LinearNoBias< arma::mat, arma::mat > *, LogSoftMax< arma::mat, arma::mat > *, Lookup< arma::mat, arma::mat > *, LSTM< arma::mat, arma::mat > *, GRU< arma::mat, arma::mat > *, FastLSTM< arma::mat, arma::mat > *, MaxPooling< arma::mat, arma::mat > *, MeanPooling< arma::mat, arma::mat > *, MultiplyConstant< arma::mat, arma::mat > *, MultiplyMerge< arma::mat, arma::mat > *, NegativeLogLikelihood< arma::mat, arma::mat > *, PReLU< arma::mat, arma::mat > *, Recurrent< arma::mat, arma::mat > *, RecurrentAttention< arma::mat, arma::mat > *, ReinforceNormal< arma::mat, arma::mat > *, Reparametrization< arma::mat, arma::mat > *, Select< arma::mat, arma::mat > *, Sequential< arma::mat, arma::mat, false > *, Sequential< arma::mat, arma::mat, true > *, Subview< arma::mat, arma::mat > *, VRClassReward< arma::mat, arma::mat > *, CustomLayers *... >
template<class ActivationFunction = RectifierFunction, typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
using	ReLULayer = BaseLayer< ActivationFunction, InputDataType, OutputDataType >
	Standard rectified linear unit non-linearity layer. More...
template<typename InputDataType = arma::mat, typename OutputDataType = arma::mat, typename... CustomLayers>
using	Residual = Sequential< InputDataType, OutputDataType, true, CustomLayers...>
using	SELU = ELU< arma::mat, arma::mat >
template<class ActivationFunction = LogisticFunction, typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
using	SigmoidLayer = BaseLayer< ActivationFunction, InputDataType, OutputDataType >
	Standard Sigmoid-Layer using the logistic activation function. More...
template<class ActivationFunction = SoftplusFunction, typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
using	SoftPlusLayer = BaseLayer< ActivationFunction, InputDataType, OutputDataType >
	Standard Softplus-Layer using the Softplus activation function. More...
template<class ActivationFunction = TanhFunction, typename InputDataType = arma::mat, typename OutputDataType = arma::mat>
using	TanHLayer = BaseLayer< ActivationFunction, InputDataType, OutputDataType >
	Standard hyperbolic tangent layer. More...
using	XavierInitialization = GlorotInitializationType< true >
	XavierInitilization is the popular name for this method. More...

Functions
	HAS_ANY_METHOD_FORM (Model, HasModelCheck)
	HAS_MEM_FUNC (Gradient, HasGradientCheck)
	HAS_MEM_FUNC (Deterministic, HasDeterministicCheck)
	HAS_MEM_FUNC (Parameters, HasParametersCheck)
	HAS_MEM_FUNC (Add, HasAddCheck)
	HAS_MEM_FUNC (Location, HasLocationCheck)
	HAS_MEM_FUNC (Reset, HasResetCheck)
	HAS_MEM_FUNC (ResetCell, HasResetCellCheck)
	HAS_MEM_FUNC (Reward, HasRewardCheck)
	HAS_MEM_FUNC (InputWidth, HasInputWidth)
	HAS_MEM_FUNC (InputHeight, HasInputHeight)
	HAS_MEM_FUNC (Rho, HasRho)
	HAS_MEM_FUNC (Loss, HasLoss)
	HAS_MEM_FUNC (Run, HasRunCheck)

Detailed Description

Artificial Neural Network.

Typedef Documentation

using CustomLayer = BaseLayer< ActivationFunction, InputDataType, OutputDataType>

Standard Sigmoid layer.

Definition at line 31 of file custom_layer.hpp.

using Embedding = Lookup<MatType, MatType>

Definition at line 131 of file lookup.hpp.

using GlorotInitialization = GlorotInitializationType<false>

GlorotInitialization uses uniform distribution.

Definition at line 148 of file glorot_init.hpp.

using HardSigmoidLayer = BaseLayer< ActivationFunction, InputDataType, OutputDataType>

Standard HardSigmoid-Layer using the HardSigmoid activation function.

Definition at line 185 of file base_layer.hpp.

using IdentityLayer = BaseLayer< ActivationFunction, InputDataType, OutputDataType>

Standard Identity-Layer using the identity activation function.

Definition at line 141 of file base_layer.hpp.

using LayerTypes = boost::variant< Add<arma::mat, arma::mat>*, AddMerge<arma::mat, arma::mat>*, AtrousConvolution<NaiveConvolution<ValidConvolution>, NaiveConvolution<FullConvolution>, NaiveConvolution<ValidConvolution>, arma::mat, arma::mat>*, BaseLayer<LogisticFunction, arma::mat, arma::mat>*, BaseLayer<IdentityFunction, arma::mat, arma::mat>*, BaseLayer<TanhFunction, arma::mat, arma::mat>*, BaseLayer<RectifierFunction, arma::mat, arma::mat>*, BaseLayer<SoftplusFunction, arma::mat, arma::mat>*, BatchNorm<arma::mat, arma::mat>*, BilinearInterpolation<arma::mat, arma::mat>*, Concat<arma::mat, arma::mat>*, Concatenate<arma::mat, arma::mat>*, ConcatPerformance<NegativeLogLikelihood<arma::mat, arma::mat>, arma::mat, arma::mat>*, Constant<arma::mat, arma::mat>*, Convolution<NaiveConvolution<ValidConvolution>, NaiveConvolution<FullConvolution>, NaiveConvolution<ValidConvolution>, arma::mat, arma::mat>*, TransposedConvolution<NaiveConvolution<ValidConvolution>, NaiveConvolution<FullConvolution>, NaiveConvolution<ValidConvolution>, arma::mat, arma::mat>*, DropConnect<arma::mat, arma::mat>*, Dropout<arma::mat, arma::mat>*, AlphaDropout<arma::mat, arma::mat>*, ELU<arma::mat, arma::mat>*, FlexibleReLU<arma::mat, arma::mat>*, Glimpse<arma::mat, arma::mat>*, HardTanH<arma::mat, arma::mat>*, Join<arma::mat, arma::mat>*, LayerNorm<arma::mat, arma::mat>*, LeakyReLU<arma::mat, arma::mat>*, CReLU<arma::mat, arma::mat>*, Linear<arma::mat, arma::mat>*, LinearNoBias<arma::mat, arma::mat>*, LogSoftMax<arma::mat, arma::mat>*, Lookup<arma::mat, arma::mat>*, LSTM<arma::mat, arma::mat>*, GRU<arma::mat, arma::mat>*, FastLSTM<arma::mat, arma::mat>*, MaxPooling<arma::mat, arma::mat>*, MeanPooling<arma::mat, arma::mat>*, MultiplyConstant<arma::mat, arma::mat>*, MultiplyMerge<arma::mat, arma::mat>*, NegativeLogLikelihood<arma::mat, arma::mat>*, PReLU<arma::mat, arma::mat>*, Recurrent<arma::mat, arma::mat>*, RecurrentAttention<arma::mat, arma::mat>*, ReinforceNormal<arma::mat, arma::mat>*, Reparametrization<arma::mat, arma::mat>*, Select<arma::mat, arma::mat>*, Sequential<arma::mat, arma::mat, false>*, Sequential<arma::mat, arma::mat, true>*, Subview<arma::mat, arma::mat>*, VRClassReward<arma::mat, arma::mat>*, CustomLayers*... >

Definition at line 203 of file layer_types.hpp.

using ReLULayer = BaseLayer< ActivationFunction, InputDataType, OutputDataType>

Standard rectified linear unit non-linearity layer.

Definition at line 152 of file base_layer.hpp.

using Residual = Sequential< InputDataType, OutputDataType, true, CustomLayers...>

Definition at line 241 of file sequential.hpp.

using SELU = ELU<arma::mat, arma::mat>

Definition at line 263 of file elu.hpp.

using SigmoidLayer = BaseLayer< ActivationFunction, InputDataType, OutputDataType>

Standard Sigmoid-Layer using the logistic activation function.

Definition at line 130 of file base_layer.hpp.

using SoftPlusLayer = BaseLayer< ActivationFunction, InputDataType, OutputDataType>

Standard Softplus-Layer using the Softplus activation function.

Definition at line 174 of file base_layer.hpp.

using TanHLayer = BaseLayer< ActivationFunction, InputDataType, OutputDataType>

Standard hyperbolic tangent layer.

Definition at line 163 of file base_layer.hpp.

using XavierInitialization = GlorotInitializationType<true>

XavierInitilization is the popular name for this method.

Definition at line 143 of file glorot_init.hpp.

Function Documentation

mlpack::ann::HAS_ANY_METHOD_FORM	(	Model	,
		HasModelCheck
	)

mlpack::ann::HAS_MEM_FUNC	(	Gradient	,
		HasGradientCheck
	)

mlpack::ann::HAS_MEM_FUNC	(	Deterministic	,
		HasDeterministicCheck
	)

mlpack::ann::HAS_MEM_FUNC	(	Parameters	,
		HasParametersCheck
	)

mlpack::ann::HAS_MEM_FUNC	(	Add	,
		HasAddCheck
	)

mlpack::ann::HAS_MEM_FUNC	(	Location	,
		HasLocationCheck
	)

mlpack::ann::HAS_MEM_FUNC	(	Reset	,
		HasResetCheck
	)

mlpack::ann::HAS_MEM_FUNC	(	ResetCell	,
		HasResetCellCheck
	)

mlpack::ann::HAS_MEM_FUNC	(	Reward	,
		HasRewardCheck
	)

mlpack::ann::HAS_MEM_FUNC	(	InputWidth	,
		HasInputWidth
	)

mlpack::ann::HAS_MEM_FUNC	(	InputHeight	,
		HasInputHeight
	)

mlpack::ann::HAS_MEM_FUNC	(	Rho	,
		HasRho
	)

mlpack::ann::HAS_MEM_FUNC	(	Loss	,
		HasLoss
	)

mlpack::ann::HAS_MEM_FUNC	(	Run	,
		HasRunCheck
	)