stub for the RBM class. at the moment it is just a holder of the parameter set and the Energy. More...

#include <shark/Unsupervised/RBM/RBM.h>

Inheritance diagram for shark::RBM< VisibleLayerT, HiddenLayerT, randomT >:

Public Types
typedef HiddenLayerT	HiddenType
	type of the hidden layer More...

typedef VisibleLayerT	VisibleType
	type of the visible layer More...

typedef randomT	randomType

typedef Energy< RBM< VisibleType, HiddenType, randomT > >	EnergyType
	Type of the energy function. More...

typedef detail::AverageEnergyGradient< RBM >	GradientType
	Type of the gradient calculator. More...

typedef base_type::BatchInputType	BatchInputType

typedef base_type::BatchOutputType	BatchOutputType

Public Types inherited from shark::AbstractModel< RealVector, RealVector >
enum	Feature

typedef RealVector	InputType
	Defines the input type of the model. More...

typedef RealVector	OutputType
	Defines the output type of the model. More...

typedef AbstractModel< RealVector, RealVector, RealVector >	ModelBaseType
	Defines the BaseType used by the model (this type). Useful for creating derived models. More...

typedef Batch< InputType >::type	BatchInputType
	defines the batch type of the input type. More...

typedef Batch< OutputType >::type	BatchOutputType
	defines the batch type of the output type More...

typedef TypedFlags< Feature >	Features

typedef TypedFeatureNotAvailableException< Feature >	FeatureNotAvailableException

Public Types inherited from shark::IParameterizable< RealVector >
typedef RealVector	ParameterVectorType

Public Member Functions
	RBM (randomType &rng)

std::string	name () const
	From INameable: return the class name. More...

std::size_t	numberOfParameters () const
	Returns the total number of parameters of the model. More...

RealVector	parameterVector () const
	Returns the parameters of the Model as parameter vector. More...

void	setParameterVector (const RealVector &newParameters)
	Sets the parameters of the model. More...

void	setStructure (std::size_t visibleNeurons, std::size_t hiddenNeurons)
	Creates the structure of the RBM. More...

HiddenType const &	hiddenNeurons () const
	Returns the layer of hidden neurons. More...

HiddenType &	hiddenNeurons ()
	Returns the layer of hidden neurons. More...

VisibleType &	visibleNeurons ()
	Returns the layer of visible neurons. More...

VisibleType const &	visibleNeurons () const
	Returns the layer of visible neurons. More...

RealMatrix &	weightMatrix ()
	Returns the weight matrix connecting the layers. More...

RealMatrix const &	weightMatrix () const
	Returns the weight matrix connecting the layers. More...

EnergyType	energy () const
	Returns the energy function of the RBM. More...

randomType &	rng ()
	Returns the random number generator associated with this RBM. More...

void	evaluationType (bool forward, bool evalMean)
	Sets the type of evaluation, eval will perform. More...

Shape	outputShape () const
	Returns the shape of the output. More...

Shape	inputShape () const
	Returns the expected shape of the input. More...

boost::shared_ptr< State >	createState () const
	Creates an internal state of the model. More...

void	eval (BatchInputType const &patterns, BatchOutputType &outputs) const
	Passes information through/samples from an RBM in a forward or backward way. More...

void	eval (BatchInputType const &patterns, BatchOutputType &outputs, State &state) const
	Standard interface for evaluating the response of the model to a batch of patterns. More...

void	inputHidden (RealMatrix &inputs, RealMatrix const &visibleStates) const
	Calculates the input of the hidden neurons given the state of the visible in a batch-vise fassion. More...

void	inputVisible (RealMatrix &inputs, RealMatrix const &hiddenStates) const
	Calculates the input of the visible neurons given the state of the hidden. More...

std::size_t	numberOfHN () const
	Returns the number of hidden Neurons. More...

std::size_t	numberOfVN () const
	Returns the number of visible Neurons. More...

void	read (InArchive &archive)
	Reads the network from an archive. More...

void	write (OutArchive &archive) const
	Writes the network to an archive. More...

Public Member Functions inherited from shark::AbstractModel< RealVector, RealVector >
	AbstractModel ()

virtual	~AbstractModel ()

const Features &	features () const

virtual void	updateFeatures ()

bool	hasFirstParameterDerivative () const
	Returns true when the first parameter derivative is implemented. More...

bool	hasFirstInputDerivative () const
	Returns true when the first input derivative is implemented. More...

virtual void	eval (InputType const &pattern, OutputType &output) const
	Standard interface for evaluating the response of the model to a single pattern. More...

Data< OutputType >	operator() (Data< InputType > const &patterns) const
	Model evaluation as an operator for a whole dataset. This is a convenience function. More...

OutputType	operator() (InputType const &pattern) const
	Model evaluation as an operator for a single pattern. This is a convenience function. More...

BatchOutputType	operator() (BatchInputType const &patterns) const
	Model evaluation as an operator for a single pattern. This is a convenience function. More...

virtual void	weightedParameterDerivative (BatchInputType const &pattern, BatchOutputType const &outputs, BatchOutputType const &coefficients, State const &state, RealVector &derivative) const
	calculates the weighted sum of derivatives w.r.t the parameters. More...

virtual void	weightedInputDerivative (BatchInputType const &pattern, BatchOutputType const &outputs, BatchOutputType const &coefficients, State const &state, BatchInputType &derivative) const
	calculates the weighted sum of derivatives w.r.t the inputs More...

virtual void	weightedDerivatives (BatchInputType const &patterns, BatchOutputType const &outputs, BatchOutputType const &coefficients, State const &state, RealVector &parameterDerivative, BatchInputType &inputDerivative) const
	calculates weighted input and parameter derivative at the same time More...

Public Member Functions inherited from shark::IParameterizable< RealVector >
virtual	~IParameterizable ()

Public Member Functions inherited from shark::INameable
virtual	~INameable ()

Public Member Functions inherited from shark::ISerializable
virtual	~ISerializable ()
	Virtual d'tor. More...

void	load (InArchive &archive, unsigned int version)
	Versioned loading of components, calls read(...). More...

void	save (OutArchive &archive, unsigned int version) const
	Versioned storing of components, calls write(...). More...

	BOOST_SERIALIZATION_SPLIT_MEMBER ()

Additional Inherited Members
Protected Attributes inherited from shark::AbstractModel< RealVector, RealVector >
Features	m_features

Detailed Description

template<class VisibleLayerT, class HiddenLayerT, class randomT>
class shark::RBM< VisibleLayerT, HiddenLayerT, randomT >

stub for the RBM class. at the moment it is just a holder of the parameter set and the Energy.

Definition at line 43 of file RBM.h.

Member Typedef Documentation

◆ BatchInputType

template<class VisibleLayerT , class HiddenLayerT , class randomT >

typedef base_type::BatchInputType shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::BatchInputType

Definition at line 53 of file RBM.h.

◆ BatchOutputType

template<class VisibleLayerT , class HiddenLayerT , class randomT >

typedef base_type::BatchOutputType shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::BatchOutputType

Definition at line 54 of file RBM.h.

◆ EnergyType

template<class VisibleLayerT , class HiddenLayerT , class randomT >

typedef Energy<RBM<VisibleType,HiddenType,randomT> > shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::EnergyType

Type of the energy function.

Definition at line 50 of file RBM.h.

◆ GradientType

template<class VisibleLayerT , class HiddenLayerT , class randomT >

typedef detail::AverageEnergyGradient<RBM> shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::GradientType

Type of the gradient calculator.

Definition at line 51 of file RBM.h.

◆ HiddenType

template<class VisibleLayerT , class HiddenLayerT , class randomT >

typedef HiddenLayerT shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::HiddenType

type of the hidden layer

Definition at line 47 of file RBM.h.

◆ randomType

template<class VisibleLayerT , class HiddenLayerT , class randomT >

typedef randomT shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::randomType

Definition at line 49 of file RBM.h.

◆ VisibleType

template<class VisibleLayerT , class HiddenLayerT , class randomT >

typedef VisibleLayerT shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::VisibleType

type of the visible layer

Definition at line 48 of file RBM.h.

Constructor & Destructor Documentation

◆ RBM()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::RBM ( randomType & rng )

inline

Definition at line 112 of file RBM.h.

Member Function Documentation

◆ createState()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

boost::shared_ptr<State> shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::createState ( ) const

inlinevirtual

Creates an internal state of the model.

The state is needed when the derivatives are to be calculated. Eval can store a state which is then reused to speed up the calculations of the derivatives. This also allows eval to be evaluated in parallel!

Reimplemented from shark::AbstractModel< RealVector, RealVector >.

Definition at line 226 of file RBM.h.

◆ energy()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

EnergyType shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::energy ( ) const

inline

Returns the energy function of the RBM.

Definition at line 185 of file RBM.h.

◆ eval() [1/2]

template<class VisibleLayerT , class HiddenLayerT , class randomT >

void shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::eval	(	BatchInputType const &	patterns,
		BatchOutputType &	outputs
	)		const

inlinevirtual

Passes information through/samples from an RBM in a forward or backward way.

Eval performs its operation based on the given evaluation type. There are two ways to pass data through an RBM: either forward, setting the states of the visible neurons and sample the hidden states or backwards, where the state of the hidden is fixed and the visible are sampled. Instead of the state of the hidden/visible, one often wants the mean of the state \( E_{p(h|v)}\left(h\right)\). By default, the RBM uses the forward evaluation and returns the mean of the state, but other evaluation modes can be set by evaluationType().

Parameters

patterns	the batch of (visible or hidden) inputs
outputs	the batch of (visible or hidden) outputs

Reimplemented from shark::AbstractModel< RealVector, RealVector >.

Definition at line 242 of file RBM.h.

Referenced by shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::eval().

◆ eval() [2/2]

template<class VisibleLayerT , class HiddenLayerT , class randomT >

void shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::eval	(	BatchInputType const &	patterns,
		BatchOutputType &	outputs,
		State &	state
	)		const

inlinevirtual

Standard interface for evaluating the response of the model to a batch of patterns.

Parameters

patterns	the inputs of the model
outputs	the predictions or response of the model to every pattern
state	intermediate results stored by eval which can be reused for derivative computation.

Implements shark::AbstractModel< RealVector, RealVector >.

Definition at line 252 of file RBM.h.

References shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::eval().

◆ evaluationType()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

void shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::evaluationType	(	bool	forward,
		bool	evalMean
	)

inline

Sets the type of evaluation, eval will perform.

Eval performs its operation based on the state of this function. There are two ways to pass data through an rbm: either forward, setting the states of the visible neurons and sample the hidden states or backwards, where the state of the hidden is fixed and the visible are sampled. Instead of the state of the hidden/visible, one often wants the mean of the state \( E_{p(h|v)}\left(h\right)\). By default, the RBM uses the forward evaluation and returns the mean of the state

Parameters

forward	whether the forward view should be used false=backwards
evalMean	whether the mean state should be returned. false=a sample is returned

Definition at line 205 of file RBM.h.

Referenced by main().

◆ hiddenNeurons() [1/2]

template<class VisibleLayerT , class HiddenLayerT , class randomT >

HiddenType const& shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::hiddenNeurons ( ) const

inline

Returns the layer of hidden neurons.

Definition at line 159 of file RBM.h.

Referenced by main().

◆ hiddenNeurons() [2/2]

template<class VisibleLayerT , class HiddenLayerT , class randomT >

HiddenType& shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::hiddenNeurons ( )

inline

Returns the layer of hidden neurons.

Definition at line 163 of file RBM.h.

◆ inputHidden()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

void shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::inputHidden	(	RealMatrix &	inputs,
		RealMatrix const &	visibleStates
	)		const

inline

Calculates the input of the hidden neurons given the state of the visible in a batch-vise fassion.

Parameters

inputs	the batch of vectors the input of the hidden neurons is stored in
visibleStates	the batch of states of the visible neurons

Definition at line 260 of file RBM.h.

References SIZE_CHECK.

Referenced by shark::Energy< RBM >::inputHidden().

◆ inputShape()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

Shape shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::inputShape ( ) const

inlinevirtual

Returns the expected shape of the input.

Implements shark::AbstractModel< RealVector, RealVector >.

Definition at line 218 of file RBM.h.

References shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::numberOfHN(), and shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::numberOfVN().

◆ inputVisible()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

void shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::inputVisible	(	RealMatrix &	inputs,
		RealMatrix const &	hiddenStates
	)		const

inline

Calculates the input of the visible neurons given the state of the hidden.

Parameters

inputs	the vector the input of the visible neurons is stored in
hiddenStates	the state of the hidden neurons

Definition at line 273 of file RBM.h.

References SIZE_CHECK.

Referenced by shark::Energy< RBM >::inputVisible().

◆ name()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

std::string shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::name ( ) const

inlinevirtual

From INameable: return the class name.

Reimplemented from shark::INameable.

Definition at line 116 of file RBM.h.

◆ numberOfHN()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

std::size_t shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::numberOfHN ( ) const

inline

Returns the number of hidden Neurons.

Definition at line 284 of file RBM.h.

Referenced by shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::inputShape(), shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::numberOfParameters(), shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::outputShape(), and shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::setParameterVector().

◆ numberOfParameters()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

std::size_t shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::numberOfParameters ( ) const

inlinevirtual

Returns the total number of parameters of the model.

Reimplemented from shark::IParameterizable< RealVector >.

Definition at line 120 of file RBM.h.

References shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::numberOfHN(), and shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::numberOfVN().

◆ numberOfVN()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

std::size_t shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::numberOfVN ( ) const

inline

Returns the number of visible Neurons.

Definition at line 288 of file RBM.h.

Referenced by shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::inputShape(), shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::numberOfParameters(), shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::outputShape(), and shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::setParameterVector().

◆ outputShape()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

Shape shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::outputShape ( ) const

inlinevirtual

Returns the shape of the output.

Implements shark::AbstractModel< RealVector, RealVector >.

Definition at line 210 of file RBM.h.

References shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::numberOfHN(), and shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::numberOfVN().

◆ parameterVector()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

RealVector shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::parameterVector ( ) const

inlinevirtual

Returns the parameters of the Model as parameter vector.

Reimplemented from shark::IParameterizable< RealVector >.

Definition at line 128 of file RBM.h.

◆ read()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

void shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::read ( InArchive & archive )

inlinevirtual

Reads the network from an archive.

Reimplemented from shark::AbstractModel< RealVector, RealVector >.

Definition at line 293 of file RBM.h.

◆ rng()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

randomType& shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::rng ( )

inline

Returns the random number generator associated with this RBM.

Definition at line 190 of file RBM.h.

◆ setParameterVector()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

void shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::setParameterVector ( const RealVector & newParameters )

inlinevirtual

Sets the parameters of the model.

Parameters

newParameters vector of parameters

Reimplemented from shark::IParameterizable< RealVector >.

Definition at line 137 of file RBM.h.

References shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::numberOfHN(), and shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::numberOfVN().

Referenced by trainRBM().

◆ setStructure()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

void shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::setStructure	(	std::size_t	visibleNeurons,
		std::size_t	hiddenNeurons
	)

inline

Creates the structure of the RBM.

Parameters

hiddenNeurons	number of hidden neurons.
visibleNeurons	number of visible neurons.

Definition at line 150 of file RBM.h.

Referenced by main(), and trainRBM().

◆ visibleNeurons() [1/2]

template<class VisibleLayerT , class HiddenLayerT , class randomT >

VisibleType& shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::visibleNeurons ( )

inline

Returns the layer of visible neurons.

Definition at line 167 of file RBM.h.

◆ visibleNeurons() [2/2]

template<class VisibleLayerT , class HiddenLayerT , class randomT >

VisibleType const& shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::visibleNeurons ( ) const

inline

Returns the layer of visible neurons.

Definition at line 171 of file RBM.h.

◆ weightMatrix() [1/2]

template<class VisibleLayerT , class HiddenLayerT , class randomT >

RealMatrix& shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::weightMatrix ( )

inline

Returns the weight matrix connecting the layers.

Definition at line 176 of file RBM.h.

Referenced by main().

◆ weightMatrix() [2/2]

template<class VisibleLayerT , class HiddenLayerT , class randomT >

RealMatrix const& shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::weightMatrix ( ) const

inline

Returns the weight matrix connecting the layers.

Definition at line 180 of file RBM.h.

◆ write()

template<class VisibleLayerT , class HiddenLayerT , class randomT >

void shark::RBM< VisibleLayerT, HiddenLayerT, randomT >::write ( OutArchive & archive ) const

inlinevirtual

Writes the network to an archive.

Reimplemented from shark::AbstractModel< RealVector, RealVector >.

Definition at line 307 of file RBM.h.

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

include/shark/Unsupervised/RBM/RBM.h

Public Types

Public Member Functions

Additional Inherited Members

Detailed Description

template<class VisibleLayerT, class HiddenLayerT, class randomT> class shark::RBM< VisibleLayerT, HiddenLayerT, randomT >

Member Typedef Documentation

◆ BatchInputType

◆ BatchOutputType

◆ EnergyType

◆ GradientType

◆ HiddenType

◆ randomType

◆ VisibleType

Constructor & Destructor Documentation

◆ RBM()

Member Function Documentation

◆ createState()

◆ energy()

◆ eval() [1/2]

◆ eval() [2/2]

◆ evaluationType()

◆ hiddenNeurons() [1/2]

◆ hiddenNeurons() [2/2]

◆ inputHidden()

◆ inputShape()

◆ inputVisible()

◆ name()

◆ numberOfHN()

◆ numberOfParameters()

◆ numberOfVN()

◆ outputShape()

◆ parameterVector()

◆ read()

◆ rng()

◆ setParameterVector()

◆ setStructure()

◆ visibleNeurons() [1/2]

◆ visibleNeurons() [2/2]

◆ weightMatrix() [1/2]

◆ weightMatrix() [2/2]

◆ write()

template<class VisibleLayerT, class HiddenLayerT, class randomT>
class shark::RBM< VisibleLayerT, HiddenLayerT, randomT >