Implementation of a standard recurrent neural network container. More...

Inheritance diagram for RNN< OutputLayerType, InitializationRuleType, CustomLayers >:

Public Types
using	NetworkType = RNN< OutputLayerType, InitializationRuleType, CustomLayers... >
	Convenience typedef for the internal model construction. More...

Public Member Functions
	RNN (const size_t rho, const bool single=false, OutputLayerType outputLayer=OutputLayerType(), InitializationRuleType initializeRule=InitializationRuleType())
	Create the RNN object. More...

	RNN (const RNN &)
	Copy constructor. More...

	RNN (RNN &&)
	Move constructor. More...

	~RNN ()
	Destructor to release allocated memory. More...

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

void	Add (LayerTypes< CustomLayers... > layer)

double	Evaluate (const arma::mat &parameters, const size_t begin, const size_t batchSize, const bool deterministic)
	Evaluate the recurrent neural network with the given parameters. More...

double	Evaluate (const arma::mat &parameters, const size_t begin, const size_t batchSize)
	Evaluate the recurrent neural network with the given parameters. More...

template < typename GradType >
double	EvaluateWithGradient (const arma::mat &parameters, const size_t begin, GradType &gradient, const size_t batchSize)
	Evaluate the recurrent neural network with the given parameters. More...

void	Gradient (const arma::mat &parameters, const size_t begin, arma::mat &gradient, const size_t batchSize)
	Evaluate the gradient of the recurrent neural network with the given parameters, and with respect to only one point in the dataset. More...

size_t	NumFunctions () const
	Return the number of separable functions (the number of predictor points). More...

RNN &	operator= (const RNN &)
	Copy assignment operator. More...

RNN &	operator= (RNN &&)
	Move assignment operator. More...

const arma::mat &	Parameters () const
	Return the initial point for the optimization. More...

arma::mat &	Parameters ()
	Modify the initial point for the optimization. More...

void	Predict (arma::cube predictors, arma::cube &results, const size_t batchSize=256)
	Predict the responses to a given set of predictors. More...

const arma::cube &	Predictors () const
	Get the matrix of data points (predictors). More...

arma::cube &	Predictors ()
	Modify the matrix of data points (predictors). More...

void	Reset ()
	Reset the state of the network. More...

void	ResetParameters ()
	Reset the module information (weights/parameters). More...

const arma::cube &	Responses () const
	Get the matrix of responses to the input data points. More...

arma::cube &	Responses ()
	Modify the matrix of responses to the input data points. More...

const size_t &	Rho () const
	Return the maximum length of backpropagation through time. More...

size_t &	Rho ()
	Modify the maximum length of backpropagation through time. More...

template < typename Archive >
void	serialize (Archive &ar, const uint32_t)
	Serialize the model. More...

void	Shuffle ()
	Shuffle the order of function visitation. More...

template<typename OptimizerType , typename... CallbackTypes>
double	Train (arma::cube predictors, arma::cube responses, OptimizerType &optimizer, CallbackTypes &&... callbacks)
	Train the recurrent neural network on the given input data using the given optimizer. More...

template<typename OptimizerType = ens::StandardSGD, typename... CallbackTypes>
double	Train (arma::cube predictors, arma::cube responses, CallbackTypes &&... callbacks)
	Train the recurrent neural network on the given input data. More...

template < typename OptimizerType >
std::enable_if< HasMaxIterations< OptimizerType, size_t &(OptimizerType::*)()>::value, void >::type	WarnMessageMaxIterations (OptimizerType &optimizer, size_t samples) const
	Check if the optimizer has MaxIterations() parameter, if it does then check if it's value is less than the number of datapoints in the dataset. More...

template < typename OptimizerType >
std::enable_if< !HasMaxIterations< OptimizerType, size_t &(OptimizerType::*)()>::value, void >::type	WarnMessageMaxIterations (OptimizerType &optimizer, size_t samples) const
	Check if the optimizer has MaxIterations() parameter, if it doesn't then simply return from the function. More...

Detailed Description

template<typename OutputLayerType = NegativeLogLikelihood<>, typename InitializationRuleType = RandomInitialization, typename... CustomLayers>
class mlpack::ann::RNN< OutputLayerType, InitializationRuleType, CustomLayers >

Implementation of a standard recurrent neural network container.

Template Parameters

OutputLayerType	The output layer type used to evaluate the network.
InitializationRuleType	Rule used to initialize the weight matrix.

Definition at line 45 of file rnn.hpp.

Member Typedef Documentation

◆ NetworkType

using NetworkType = RNN<OutputLayerType, InitializationRuleType, CustomLayers...>

Convenience typedef for the internal model construction.

Definition at line 51 of file rnn.hpp.

Constructor & Destructor Documentation

◆ RNN() [1/3]

RNN	(	const size_t	rho,
		const bool	single = `false`,
		OutputLayerType	outputLayer = `OutputLayerType()`,
		InitializationRuleType	initializeRule = `InitializationRuleType()`
	)

Create the RNN object.

Optionally, specify which initialize rule and performance function should be used.

If you want to pass in a parameter and discard the original parameter object, be sure to use std::move to avoid unnecessary copy.

Parameters

rho	Maximum number of steps to backpropagate through time (BPTT).
single	Predict only the last element of the input sequence.
outputLayer	Output layer used to evaluate the network.
initializeRule	Optional instantiated InitializationRule object for initializing the network parameter.

◆ RNN() [2/3]

RNN ( const RNN< OutputLayerType, InitializationRuleType, CustomLayers > & )

Copy constructor.

◆ RNN() [3/3]

RNN ( RNN< OutputLayerType, InitializationRuleType, CustomLayers > && )

Move constructor.

◆ ~RNN()

~RNN ( )

Destructor to release allocated memory.

Member Function Documentation

◆ Add() [1/2]

void Add ( Args... args )

inline

Definition at line 284 of file rnn.hpp.

◆ Add() [2/2]

void Add ( LayerTypes< CustomLayers... > layer )

inline

Definition at line 291 of file rnn.hpp.

◆ Evaluate() [1/2]

double Evaluate	(	const arma::mat &	parameters,
		const size_t	begin,
		const size_t	batchSize,
		const bool	deterministic
	)

Evaluate the recurrent neural network with the given parameters.

This function is usually called by the optimizer to train the model.

Parameters

parameters	Matrix model parameters.
begin	Index of the starting point to use for objective function evaluation.
batchSize	Number of points to be passed at a time to use for objective function evaluation.
deterministic	Whether or not to train or test the model. Note some layer act differently in training or testing mode.

◆ Evaluate() [2/2]

double Evaluate	(	const arma::mat &	parameters,
		const size_t	begin,
		const size_t	batchSize
	)

Evaluate the recurrent neural network with the given parameters.

This function is usually called by the optimizer to train the model. This just calls the other overload of Evaluate() with deterministic = true.

Parameters

parameters	Matrix model parameters.
begin	Index of the starting point to use for objective function evaluation.
batchSize	Number of points to be passed at a time to use for objective function evaluation.

◆ EvaluateWithGradient()

double EvaluateWithGradient	(	const arma::mat &	parameters,
		const size_t	begin,
		GradType &	gradient,
		const size_t	batchSize
	)

Evaluate the recurrent neural network with the given parameters.

This function is usually called by the optimizer to train the model.

Parameters

parameters	Matrix model parameters.
begin	Index of the starting point to use for objective function evaluation.
gradient	Matrix to output gradient into.
batchSize	Number of points to be passed at a time to use for objective function evaluation.

◆ Gradient()

void Gradient	(	const arma::mat &	parameters,
		const size_t	begin,
		arma::mat &	gradient,
		const size_t	batchSize
	)

Evaluate the gradient of the recurrent neural network with the given parameters, and with respect to only one point in the dataset.

This is useful for optimizers such as SGD, which require a separable objective function.

Parameters

parameters	Matrix of the model parameters to be optimized.
begin	Index of the starting point to use for objective function gradient evaluation.
gradient	Matrix to output gradient into.
batchSize	Number of points to be processed as a batch for objective function gradient evaluation.

Referenced by RNN< OutputLayerType, InitializationRuleType, CustomLayers... >::Predictors().

◆ NumFunctions()

size_t NumFunctions ( ) const

inline

Return the number of separable functions (the number of predictor points).

Definition at line 294 of file rnn.hpp.

◆ operator=() [1/2]

RNN& operator= ( const RNN< OutputLayerType, InitializationRuleType, CustomLayers > & )

Copy assignment operator.

◆ operator=() [2/2]

RNN& operator= ( RNN< OutputLayerType, InitializationRuleType, CustomLayers > && )

Move assignment operator.

◆ Parameters() [1/2]

const arma::mat& Parameters ( ) const

inline

Return the initial point for the optimization.

Definition at line 297 of file rnn.hpp.

◆ Parameters() [2/2]

arma::mat& Parameters ( )

inline

Modify the initial point for the optimization.

Definition at line 299 of file rnn.hpp.

◆ Predict()

void Predict	(	arma::cube	predictors,
		arma::cube &	results,
		const size_t	batchSize = `256`
	)

Predict the responses to a given set of predictors.

The responses will reflect the output of the given output layer as returned by the output layer function.

If you want to pass in a parameter and discard the original parameter object, be sure to use std::move to avoid unnecessary copy.

The format of the data should be as follows:

each slice should correspond to a time step
each column should correspond to a data point
each row should correspond to a dimension So, e.g., predictors(i, j, k) is the i'th dimension of the j'th data point at time slice k. The responses will be in the same format.

Parameters

predictors	Input predictors.
results	Matrix to put output predictions of responses into.
batchSize	Number of points to predict at once.

◆ Predictors() [1/2]

const arma::cube& Predictors ( ) const

inline

Get the matrix of data points (predictors).

Definition at line 312 of file rnn.hpp.

◆ Predictors() [2/2]

arma::cube& Predictors ( )

inline

Modify the matrix of data points (predictors).

Definition at line 314 of file rnn.hpp.

◆ Reset()

void Reset ( )

Reset the state of the network.

This ensures that all internally-held gradients are set to 0, all memory cells are reset, and the parameters matrix is the right size.

Referenced by RNN< OutputLayerType, InitializationRuleType, CustomLayers... >::Predictors().

◆ ResetParameters()

void ResetParameters ( )

Reset the module information (weights/parameters).

Referenced by RNN< OutputLayerType, InitializationRuleType, CustomLayers... >::Predictors().

◆ Responses() [1/2]

const arma::cube& Responses ( ) const

inline

Get the matrix of responses to the input data points.

Definition at line 307 of file rnn.hpp.

◆ Responses() [2/2]

arma::cube& Responses ( )

inline

Modify the matrix of responses to the input data points.

Definition at line 309 of file rnn.hpp.

◆ Rho() [1/2]

const size_t& Rho ( ) const

inline

Return the maximum length of backpropagation through time.

Definition at line 302 of file rnn.hpp.

◆ Rho() [2/2]

size_t& Rho ( )

inline

Modify the maximum length of backpropagation through time.

Definition at line 304 of file rnn.hpp.

◆ serialize()

void serialize	(	Archive &	ar,
		const uint32_t
	)

Serialize the model.

Referenced by RNN< OutputLayerType, InitializationRuleType, CustomLayers... >::Predictors().

◆ Shuffle()

void Shuffle ( )

Shuffle the order of function visitation.

This may be called by the optimizer.

◆ Train() [1/2]

double Train	(	arma::cube	predictors,
		arma::cube	responses,
		OptimizerType &	optimizer,
		CallbackTypes &&...	callbacks
	)

Train the recurrent neural network on the given input data using the given optimizer.

This will use the existing model parameters as a starting point for the optimization. If this is not what you want, then you should access the parameters vector directly with Parameters() and modify it as desired.

If you want to pass in a parameter and discard the original parameter object, be sure to use std::move to avoid unnecessary copy.

The format of the data should be as follows:

each slice should correspond to a time step
each column should correspond to a data point
each row should correspond to a dimension So, e.g., predictors(i, j, k) is the i'th dimension of the j'th data point at time slice k.

Template Parameters

OptimizerType	Type of optimizer to use to train the model.
CallbackTypes	Types of Callback Functions.

Parameters

predictors	Input training variables.
responses	Outputs results from input training variables.
optimizer	Instantiated optimizer used to train the model.
callbacks	Callback function for ensmallen optimizer `OptimizerType`. See https://www.ensmallen.org/docs.html#callback-documentation.

Returns: The final objective of the trained model (NaN or Inf on error).

◆ Train() [2/2]

double Train	(	arma::cube	predictors,
		arma::cube	responses,
		CallbackTypes &&...	callbacks
	)

Train the recurrent neural network on the given input data.

By default, the SGD optimization algorithm is used, but others can be specified (such as ens::RMSprop).

This will use the existing model parameters as a starting point for the optimization. If this is not what you want, then you should access the parameters vector directly with Parameters() and modify it as desired.

If you want to pass in a parameter and discard the original parameter object, be sure to use std::move to avoid unnecessary copy.

The format of the data should be as follows:

each slice should correspond to a time step
each column should correspond to a data point
each row should correspond to a dimension So, e.g., predictors(i, j, k) is the i'th dimension of the j'th data point at time slice k.

Template Parameters

OptimizerType	Type of optimizer to use to train the model.
CallbackTypes	Types of Callback Functions.

Parameters

predictors	Input training variables.
responses	Outputs results from input training variables.
callbacks	Callback function for ensmallen optimizer `OptimizerType`. See https://www.ensmallen.org/docs.html#callback-documentation.

Returns: The final objective of the trained model (NaN or Inf on error).

◆ WarnMessageMaxIterations() [1/2]

std::enable_if< HasMaxIterations<OptimizerType, size_t&(OptimizerType::*)()>::value, void>::type WarnMessageMaxIterations	(	OptimizerType &	optimizer,
		size_t	samples
	)		const

Check if the optimizer has MaxIterations() parameter, if it does then check if it's value is less than the number of datapoints in the dataset.

Template Parameters

OptimizerType Type of optimizer to use to train the model.

Parameters

optimizer	optimizer used in the training process.
samples	Number of datapoints in the dataset.

◆ WarnMessageMaxIterations() [2/2]

std::enable_if< !HasMaxIterations<OptimizerType, size_t&(OptimizerType::*)()>::value, void>::type WarnMessageMaxIterations	(	OptimizerType &	optimizer,
		size_t	samples
	)		const

Check if the optimizer has MaxIterations() parameter, if it doesn't then simply return from the function.

Template Parameters

OptimizerType Type of optimizer to use to train the model.

Parameters

optimizer	optimizer used in the training process.
samples	Number of datapoints in the dataset.

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

/home/jenkins-mlpack/mlpack.org/_src/mlpack-git/src/mlpack/methods/ann/rnn.hpp

Public Types

Public Member Functions

Detailed Description

template<typename OutputLayerType = NegativeLogLikelihood<>, typename InitializationRuleType = RandomInitialization, typename... CustomLayers> class mlpack::ann::RNN< OutputLayerType, InitializationRuleType, CustomLayers >

Member Typedef Documentation

◆ NetworkType

Constructor & Destructor Documentation

◆ RNN() [1/3]

◆ RNN() [2/3]

◆ RNN() [3/3]

◆ ~RNN()

Member Function Documentation

◆ Add() [1/2]

◆ Add() [2/2]

◆ Evaluate() [1/2]

◆ Evaluate() [2/2]

◆ EvaluateWithGradient()

◆ Gradient()

◆ NumFunctions()

◆ operator=() [1/2]

◆ operator=() [2/2]

◆ Parameters() [1/2]

◆ Parameters() [2/2]

◆ Predict()

◆ Predictors() [1/2]

◆ Predictors() [2/2]

◆ Reset()

◆ ResetParameters()

◆ Responses() [1/2]

◆ Responses() [2/2]

◆ Rho() [1/2]

◆ Rho() [2/2]

◆ serialize()

◆ Shuffle()

◆ Train() [1/2]

◆ Train() [2/2]

◆ WarnMessageMaxIterations() [1/2]

◆ WarnMessageMaxIterations() [2/2]

template<typename OutputLayerType = NegativeLogLikelihood<>, typename InitializationRuleType = RandomInitialization, typename... CustomLayers>
class mlpack::ann::RNN< OutputLayerType, InitializationRuleType, CustomLayers >