Model which corrupts the data using Impulse noise. More...

#include <shark/Models/ImpulseNoiseModel.h>

Inheritance diagram for shark::ImpulseNoiseModel:

Public Member Functions
	ImpulseNoiseModel ()
	Default Constructor; use setStructure later. More...

	ImpulseNoiseModel (unsigned int inputs, double prob, double value=0.0)
	Constructor creating a model with given input size and a probability to set values of the input to a given value. More...

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

size_t	inputSize () const
	obtain the input dimension More...

size_t	outputSize () const
	obtain the output dimension More...

RealVector	parameterVector () const
	obtain the parameter vector More...

void	setParameterVector (RealVector const &newParameters)
	overwrite the parameter vector More...

size_t	numberOfParameters () const
	return the number of parameter More...

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

void	eval (BatchInputType const &inputs, BatchOutputType &outputs) const
	Add noise to the input. More...

void	eval (BatchInputType const &inputs, BatchOutputType &outputs, State &state) const
	Evaluate the model: output = matrix * input + offset. More...

void	weightedParameterDerivative (BatchInputType const &patterns, RealVector const &coefficients, State const &state, RealVector &gradient) const

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	hasSecondParameterDerivative () const
	Returns true when the second parameter derivative is implemented. More...

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

bool	hasSecondInputDerivative () const
	Returns true when the second parameter derivative is implemented. More...

bool	isSequential () const

virtual void	read (InArchive &archive)
	From ISerializable, reads a model from an archive. More...

virtual void	write (OutArchive &archive) const
	writes a model to an archive 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 &coefficients, State const &state, RealVector &derivative) const
	calculates the weighted sum of derivatives w.r.t the parameters. More...

virtual void	weightedParameterDerivative (BatchInputType const &pattern, BatchOutputType const &coefficients, Batch< RealMatrix >::type const &errorHessian, State const &state, RealVector &derivative, RealMatrix &hessian) const
	calculates the weighted sum of derivatives w.r.t the parameters More...

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

virtual void	weightedInputDerivative (BatchInputType const &pattern, BatchOutputType const &coefficients, typename Batch< RealMatrix >::type const &errorHessian, State const &state, RealMatrix &derivative, Batch< RealMatrix >::type &hessian) const
	calculates the weighted sum of derivatives w.r.t the inputs More...

virtual void	weightedDerivatives (BatchInputType const &patterns, 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
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
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 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

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

Detailed Description

Model which corrupts the data using Impulse noise.

We define impulse noise as a noise which randomly sets the value of an element in a vector to a given value, 0 by default. We chose the name as with for example a noise of 1, impulses can be seen in the visualised vectors.

very input dimension is tested independently.

This noise can be used to implement denoising autoencoders for binary data.

Definition at line 49 of file ImpulseNoiseModel.h.

Constructor & Destructor Documentation

◆ ImpulseNoiseModel() [1/2]

shark::ImpulseNoiseModel::ImpulseNoiseModel ( )

inline

Default Constructor; use setStructure later.

Definition at line 59 of file ImpulseNoiseModel.h.

References shark::AbstractModel< RealVector, RealVector >::HAS_FIRST_PARAMETER_DERIVATIVE, and shark::AbstractModel< RealVector, RealVector >::m_features.

◆ ImpulseNoiseModel() [2/2]

shark::ImpulseNoiseModel::ImpulseNoiseModel	(	unsigned int	inputs,
		double	prob,
		double	value = `0.0`
	)

inline

Constructor creating a model with given input size and a probability to set values of the input to a given value.

Definition at line 63 of file ImpulseNoiseModel.h.

References shark::AbstractModel< RealVector, RealVector >::HAS_FIRST_PARAMETER_DERIVATIVE, and shark::AbstractModel< RealVector, RealVector >::m_features.

Member Function Documentation

◆ createState()

boost::shared_ptr<State> shark::ImpulseNoiseModel::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 97 of file ImpulseNoiseModel.h.

◆ eval() [1/2]

void shark::ImpulseNoiseModel::eval	(	BatchInputType const &	inputs,
		BatchOutputType &	outputs
	)		const

inlinevirtual

Add noise to the input.

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

Definition at line 102 of file ImpulseNoiseModel.h.

References shark::coinToss(), inputSize(), SHARK_CRITICAL_REGION, and SIZE_CHECK.

Referenced by eval().

◆ eval() [2/2]

void shark::ImpulseNoiseModel::eval	(	BatchInputType const &	inputs,
		BatchOutputType &	outputs,
		State &	state
	)		const

inlinevirtual

Evaluate the model: output = matrix * input + offset.

Implements shark::AbstractModel< RealVector, RealVector >.

Definition at line 116 of file ImpulseNoiseModel.h.

References eval().

◆ inputSize()

size_t shark::ImpulseNoiseModel::inputSize ( ) const

inline

obtain the input dimension

Definition at line 73 of file ImpulseNoiseModel.h.

Referenced by eval().

◆ name()

std::string shark::ImpulseNoiseModel::name ( ) const

inlinevirtual

From INameable: return the class name.

Reimplemented from shark::INameable.

Definition at line 69 of file ImpulseNoiseModel.h.

◆ numberOfParameters()

size_t shark::ImpulseNoiseModel::numberOfParameters ( ) const

inlinevirtual

return the number of parameter

Reimplemented from shark::IParameterizable.

Definition at line 94 of file ImpulseNoiseModel.h.

◆ outputSize()

size_t shark::ImpulseNoiseModel::outputSize ( ) const

inline

obtain the output dimension

Definition at line 78 of file ImpulseNoiseModel.h.

◆ parameterVector()

RealVector shark::ImpulseNoiseModel::parameterVector ( ) const

inlinevirtual

obtain the parameter vector

Reimplemented from shark::IParameterizable.

Definition at line 83 of file ImpulseNoiseModel.h.

◆ setParameterVector()

void shark::ImpulseNoiseModel::setParameterVector ( RealVector const & newParameters )

inlinevirtual

overwrite the parameter vector

Reimplemented from shark::IParameterizable.

Definition at line 88 of file ImpulseNoiseModel.h.

References SIZE_CHECK.

◆ weightedParameterDerivative()

void shark::ImpulseNoiseModel::weightedParameterDerivative	(	BatchInputType const &	patterns,
		RealVector const &	coefficients,
		State const &	state,
		RealVector &	gradient
	)		const

inline

Definition at line 120 of file ImpulseNoiseModel.h.

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

include/shark/Models/ImpulseNoiseModel.h

Public Member Functions

Additional Inherited Members

Detailed Description

Constructor & Destructor Documentation

◆ ImpulseNoiseModel() [1/2]

◆ ImpulseNoiseModel() [2/2]

Member Function Documentation

◆ createState()

◆ eval() [1/2]

◆ eval() [2/2]

◆ inputSize()

◆ name()

◆ numberOfParameters()

◆ outputSize()

◆ parameterVector()

◆ setParameterVector()

◆ weightedParameterDerivative()