Implementation of a standard feed forward network. More...

#include <ffn.hpp>

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

Public Member Functions
	FFN (OutputLayerType outputLayer=OutputLayerType(), InitializationRuleType initializeRule=InitializationRuleType())
	Create the FFN object. More...

	FFN (const FFN &)
	Copy constructor.

	FFN (FFN &&)
	Move constructor.

FFN &	operator= (FFN)
	Copy/move assignment operator.

	~FFN ()
	Destructor to release allocated memory.

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...

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

template<typename OptimizerType = ens::RMSProp, typename... CallbackTypes>
double	Train (arma::mat predictors, arma::mat responses, CallbackTypes &&... callbacks)
	Train the feedforward network on the given input data. More...

void	Predict (arma::mat predictors, arma::mat &results)
	Predict the responses to a given set of predictors. More...

template<typename PredictorsType , typename ResponsesType >
double	Evaluate (const PredictorsType &predictors, const ResponsesType &responses)
	Evaluate the feedforward network with the given predictors and responses. More...

double	Evaluate (const arma::mat &parameters)
	Evaluate the feedforward network with the given parameters. More...

double	Evaluate (const arma::mat &parameters, const size_t begin, const size_t batchSize, const bool deterministic)
	Evaluate the feedforward network with the given parameters, but using only a number of data points. More...

double	Evaluate (const arma::mat &parameters, const size_t begin, const size_t batchSize)
	Evaluate the feedforward network with the given parameters, but using only a number of data points. More...

template<typename GradType >
double	EvaluateWithGradient (const arma::mat &parameters, GradType &gradient)
	Evaluate the feedforward 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 feedforward network with the given parameters, but using only a number of data points. More...

void	Gradient (const arma::mat &parameters, const size_t begin, arma::mat &gradient, const size_t batchSize)
	Evaluate the gradient of the feedforward network with the given parameters, and with respect to only a number of points in the dataset. More...

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

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

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

const std::vector< LayerTypes< CustomLayers... > > &	Model () const
	Get the network model.

std::vector< LayerTypes< CustomLayers... > > &	Model ()
	Modify the network model. More...

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

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

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

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

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

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

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

void	ResetParameters ()
	Reset the module infomration (weights/parameters).

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

template<typename PredictorsType , typename ResponsesType >
void	Forward (const PredictorsType &inputs, ResponsesType &results)
	Perform the forward pass of the data in real batch mode. More...

template<typename PredictorsType , typename ResponsesType >
void	Forward (const PredictorsType &inputs, ResponsesType &results, const size_t begin, const size_t end)
	Perform a partial forward pass of the data. More...

template<typename PredictorsType , typename TargetsType , typename GradientsType >
double	Backward (const PredictorsType &inputs, const TargetsType &targets, GradientsType &gradients)
	Perform the backward pass of the data in real batch mode. More...

Friends
template<typename Model , typename InitializerType , typename NoiseType , typename PolicyType >
class	GAN

Detailed Description

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

Implementation of a standard feed forward network.

Template Parameters

OutputLayerType	The output layer type used to evaluate the network.
InitializationRuleType	Rule used to initialize the weight matrix.
CustomLayers	Any set of custom layers that could be a part of the feed forward network.

Constructor & Destructor Documentation

◆ FFN()

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::FFN	(	OutputLayerType	outputLayer = `OutputLayerType()`,
		InitializationRuleType	initializeRule = `InitializationRuleType()`
	)

Create the FFN 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

outputLayer	Output layer used to evaluate the network.
initializeRule	Optional instantiated InitializationRule object for initializing the network parameter.

Member Function Documentation

◆ Backward()

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

template<typename PredictorsType , typename TargetsType , typename GradientsType >

double mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::Backward	(	const PredictorsType &	inputs,
		const TargetsType &	targets,
		GradientsType &	gradients
	)

Perform the backward pass of the data in real batch mode.

Forward and Backward should be used as a pair, and they are designed mainly for advanced users. User should try to use Predict and Train unless those two functions can't satisfy some special requirements.

Parameters

inputs	Inputs of current pass.
targets	The training target.
gradients	Computed gradients.

Returns: Training error of the current pass.

◆ Evaluate() [1/4]

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

template<typename PredictorsType , typename ResponsesType >

double mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::Evaluate	(	const PredictorsType &	predictors,
		const ResponsesType &	responses
	)

Evaluate the feedforward network with the given predictors and responses.

This functions is usually used to monitor progress while training.

Parameters

predictors	Input variables.
responses	Target outputs for input variables.

◆ Evaluate() [2/4]

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

double mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::Evaluate ( const arma::mat & parameters )

Evaluate the feedforward network with the given parameters.

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

Parameters

parameters Matrix model parameters.

◆ Evaluate() [3/4]

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

double mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::Evaluate	(	const arma::mat &	parameters,
		const size_t	begin,
		const size_t	batchSize,
		const bool	deterministic
	)

Evaluate the feedforward network with the given parameters, but using only a number of data points.

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

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() [4/4]

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

double mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::Evaluate	(	const arma::mat &	parameters,
		const size_t	begin,
		const size_t	batchSize
	)

Evaluate the feedforward network with the given parameters, but using only a number of data points.

This is useful for optimizers such as SGD, which require a separable objective function. This just calls the 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() [1/2]

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

template<typename GradType >

double mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::EvaluateWithGradient	(	const arma::mat &	parameters,
		GradType &	gradient
	)

Evaluate the feedforward network with the given parameters.

This function is usually called by the optimizer to train the model. This just calls the overload of EvaluateWithGradient() with batchSize = 1.

Parameters

parameters	Matrix model parameters.
gradient	Matrix to output gradient into.

◆ EvaluateWithGradient() [2/2]

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

template<typename GradType >

double mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::EvaluateWithGradient	(	const arma::mat &	parameters,
		const size_t	begin,
		GradType &	gradient,
		const size_t	batchSize
	)

Evaluate the feedforward network with the given parameters, but using only a number of data points.

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

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.

◆ Forward() [1/2]

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

template<typename PredictorsType , typename ResponsesType >

void mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::Forward	(	const PredictorsType &	inputs,
		ResponsesType &	results
	)

Perform the forward pass of the data in real batch mode.

Forward and Backward should be used as a pair, and they are designed mainly for advanced users. User should try to use Predict and Train unless those two functions can't satisfy some special requirements.

Parameters

inputs	The input data.
results	The predicted results.

◆ Forward() [2/2]

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

template<typename PredictorsType , typename ResponsesType >

void mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::Forward	(	const PredictorsType &	inputs,
		ResponsesType &	results,
		const size_t	begin,
		const size_t	end
	)

Perform a partial forward pass of the data.

This function is meant for the cases when users require a forward pass only through certain layers and not the entire network.

Parameters

inputs	The input data for the specified first layer.
results	The predicted results from the specified last layer.
begin	The index of the first layer.
end	The index of the last layer.

◆ Gradient()

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

void mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::Gradient	(	const arma::mat &	parameters,
		const size_t	begin,
		arma::mat &	gradient,
		const size_t	batchSize
	)

Evaluate the gradient of the feedforward network with the given parameters, and with respect to only a number of points 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.

◆ Model()

template<typename OutputLayerType = NegativeLogLikelihood<>, typename InitializationRuleType = RandomInitialization, typename... CustomLayers>

std::vector<LayerTypes<CustomLayers...> >& mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::Model ( )

inline

Modify the network model.

Be careful! If you change the structure of the network or parameters for layers, its state may become invalid, so be sure to call ResetParameters() afterwards.

◆ Predict()

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

void mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::Predict	(	arma::mat	predictors,
		arma::mat &	results
	)

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.

Parameters

predictors	Input predictors.
results	Matrix to put output predictions of responses into.

◆ Shuffle()

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

void mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::Shuffle ( )

Shuffle the order of function visitation.

This may be called by the optimizer.

◆ Train() [1/2]

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

template<typename OptimizerType , typename... CallbackTypes>

double mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::Train	(	arma::mat	predictors,
		arma::mat	responses,
		OptimizerType &	optimizer,
		CallbackTypes &&...	callbacks
	)

Train the feedforward 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.

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]

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

template<typename OptimizerType , typename... CallbackTypes>

double mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::Train	(	arma::mat	predictors,
		arma::mat	responses,
		CallbackTypes &&...	callbacks
	)

Train the feedforward network on the given input data.

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

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.

Template Parameters

OptimizerType Type of optimizer to use to train the model.

Parameters

predictors Input training variables.

Template Parameters

CallbackTypes Types of Callback Functions.

Parameters

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]

template<typename OutputLayerType , typename InitializationRuleType , typename... CustomLayers>

template<typename OptimizerType >

std::enable_if< !HasMaxIterations< OptimizerType, size_t &(OptimizerType::*)()>::value, void >::type mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::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]

template<typename OutputLayerType = NegativeLogLikelihood<>, typename InitializationRuleType = RandomInitialization, typename... CustomLayers>

template<typename OptimizerType >

std::enable_if< !HasMaxIterations<OptimizerType, size_t&(OptimizerType::*)()>::value, void>::type mlpack::ann::FFN< OutputLayerType, InitializationRuleType, CustomLayers >::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 files:

src/mlpack/methods/ann/ffn.hpp
src/mlpack/methods/ann/ffn_impl.hpp

Public Types

Public Member Functions

Friends

Detailed Description

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

Constructor & Destructor Documentation

◆ FFN()

Member Function Documentation

◆ Backward()

◆ Evaluate() [1/4]

◆ Evaluate() [2/4]

◆ Evaluate() [3/4]

◆ Evaluate() [4/4]

◆ EvaluateWithGradient() [1/2]

◆ EvaluateWithGradient() [2/2]

◆ Forward() [1/2]

◆ Forward() [2/2]

◆ Gradient()

◆ Model()

◆ Predict()

◆ 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::FFN< OutputLayerType, InitializationRuleType, CustomLayers >