A layer of truncated exponential neurons. More...

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

Inheritance diagram for shark::TruncatedExponentialLayer:

Public Types
typedef RealSpace	StateSpace
	the state space of this neuron is real valued, so it can't be enumerated More...

typedef detail::TruncatedExponentialSufficientStatistics< RealVector >	SufficientStatistics
	Stores lambda, the defining parameter of the statistics and also exp(-lambda) since it is used regularly. More...

typedef Batch< SufficientStatistics >::type	StatisticsBatch
	Sufficient statistics of a batch of data. More...

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

Public Member Functions
const RealVector &	bias () const
	Returns the bias values of the units. More...

RealVector &	bias ()
	Returns the bias values of the units. More...

void	resize (std::size_t newSize)
	Resizes this neuron layer. More...

std::size_t	size () const
	Returns the number of neurons of this layer. More...

template<class Input , class BetaVector >
void	sufficientStatistics (Input const &input, StatisticsBatch &statistics, BetaVector const &beta) const
	Takes the input of the neuron and calculates the statistics required to sample from the conditional distribution. More...

template<class Matrix , class Rng >
void	sample (StatisticsBatch const &statistics, Matrix &state, double alpha, Rng &rng) const
	Samples from the truncated exponential distribution using either Gibbs- or flip-the-state sampling given the sufficient statistics (i.e. the parameter lambda and the value of exp(-lambda)) More...

template<class Matrix >
Matrix const &	phi (Matrix const &state) const
	Transforms the current state of the neurons for the multiplication with the weight matrix of the RBM, i.e. calculates the value of the phi-function used in the interaction term. More...

RealMatrix	expectedPhiValue (StatisticsBatch const &statistics) const
	Returns the conditional expectation of the phi-function given the state of the connected layer. More...

RealMatrix	mean (StatisticsBatch const &statistics) const
	Returns the mean of the conditional distribution. More...

template<class Matrix , class BetaVector >
RealVector	energyTerm (Matrix const &state, BetaVector const &beta) const
	Returns the energy term this neuron adds to the energy function. More...

template<class Input >
double	logMarginalize (const Input &inputs, double beta) const
	Integrates over the terms of the Energy function which depend on the state of this layer and returns the logarithm of the result. More...

template<class Vector , class SampleBatch >
void	expectedParameterDerivative (Vector &derivative, SampleBatch const &samples) const
	Calculates the expectation of the derivatives of the energy term of this neuron layer with respect to it's parameters - the bias weights. The expectation is taken with respect to the conditional probability distribution of the layer given the state of the connected layer. More...

template<class Vector , class SampleBatch >
void	parameterDerivative (Vector &derivative, SampleBatch const &samples) const
	Calculates the derivatives of the energy term of this neuron layer with respect to it's parameters - the bias weights. More...

RealVector	parameterVector () const
	Returns the vector with the parameters associated with the neurons in the layer. More...

void	setParameterVector (RealVector const &newParameters)
	Returns the vector with the parameters associated with the neurons in the layer. More...

std::size_t	numberOfParameters () const
	Returns the number of the parameters associated with the neurons in the layer. More...

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

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

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 ()

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

Detailed Description

A layer of truncated exponential neurons.

Truncated exponential distributions arise, when the state space of the binary neurons is extended to the real numbers in [0,1]. The conditional distribution of the state of this neurons given the states of the connecred layer is an exponential distribution restricted to [0,1].

Definition at line 73 of file TruncatedExponentialLayer.h.

Member Typedef Documentation

◆ StateSpace

typedef RealSpace shark::TruncatedExponentialLayer::StateSpace

the state space of this neuron is real valued, so it can't be enumerated

Definition at line 78 of file TruncatedExponentialLayer.h.

◆ StatisticsBatch

typedef Batch<SufficientStatistics>::type shark::TruncatedExponentialLayer::StatisticsBatch

Sufficient statistics of a batch of data.

Definition at line 83 of file TruncatedExponentialLayer.h.

◆ SufficientStatistics

typedef detail::TruncatedExponentialSufficientStatistics<RealVector> shark::TruncatedExponentialLayer::SufficientStatistics

Stores lambda, the defining parameter of the statistics and also exp(-lambda) since it is used regularly.

Definition at line 81 of file TruncatedExponentialLayer.h.

Member Function Documentation

◆ bias() [1/2]

const RealVector& shark::TruncatedExponentialLayer::bias ( ) const

inline

Returns the bias values of the units.

Definition at line 86 of file TruncatedExponentialLayer.h.

◆ bias() [2/2]

RealVector& shark::TruncatedExponentialLayer::bias ( )

inline

Returns the bias values of the units.

Definition at line 90 of file TruncatedExponentialLayer.h.

◆ energyTerm()

template<class Matrix , class BetaVector >

RealVector shark::TruncatedExponentialLayer::energyTerm	(	Matrix const &	state,
		BetaVector const &	beta
	)		const

inline

Returns the energy term this neuron adds to the energy function.

Parameters

state	the state of the neuron layer
beta	the inverse temperature of the i-th state

Returns: the energy term of the neuron layer

Definition at line 197 of file TruncatedExponentialLayer.h.

References SIZE_CHECK.

◆ expectedParameterDerivative()

template<class Vector , class SampleBatch >

void shark::TruncatedExponentialLayer::expectedParameterDerivative	(	Vector &	derivative,
		SampleBatch const &	samples
	)		const

inline

Calculates the expectation of the derivatives of the energy term of this neuron layer with respect to it's parameters - the bias weights. The expectation is taken with respect to the conditional probability distribution of the layer given the state of the connected layer.

This function takes a batch of samples and extracts the required informations out of it.

Parameters

derivative	the derivative with respect to the parameters, the result is added on top of it to accumulate derivatives
samples	the samples from which the informations can be extracted

Definition at line 244 of file TruncatedExponentialLayer.h.

References SIZE_CHECK.

◆ expectedPhiValue()

RealMatrix shark::TruncatedExponentialLayer::expectedPhiValue ( StatisticsBatch const & statistics ) const

inline

Returns the conditional expectation of the phi-function given the state of the connected layer.

Parameters

statistics the sufficient statistics of the layer

Definition at line 171 of file TruncatedExponentialLayer.h.

References shark::batchSize(), shark::mean(), and SIZE_CHECK.

◆ logMarginalize()

template<class Input >

double shark::TruncatedExponentialLayer::logMarginalize	(	const Input &	inputs,
		double	beta
	)		const

inline

Integrates over the terms of the Energy function which depend on the state of this layer and returns the logarithm of the result.

This function is called by Energy when the unnormalized marginal probability of the connected layer is to be computed. It calculates the part which depends on the neurons which are to be marinalized out. (In the case of the exponential hidden neuron, this is the term \( \log \int_h e^{\vec h^T W \vec v+ \vec h^T \vec c} \)).

Parameters

inputs	the inputs of the neurons they get from the other layer
beta	the inverse temperature of the RBM

Returns: the marginal distribution of the connected layer

Definition at line 217 of file TruncatedExponentialLayer.h.

References SIZE_CHECK.

◆ mean()

RealMatrix shark::TruncatedExponentialLayer::mean ( StatisticsBatch const & statistics ) const

inline

Returns the mean of the conditional distribution.

Parameters

statistics the sufficient statistics defining the conditional distribution

Definition at line 187 of file TruncatedExponentialLayer.h.

◆ numberOfParameters()

std::size_t shark::TruncatedExponentialLayer::numberOfParameters ( ) const

inlinevirtual

Returns the number of the parameters associated with the neurons in the layer.

Reimplemented from shark::IParameterizable<>.

Definition at line 272 of file TruncatedExponentialLayer.h.

◆ parameterDerivative()

template<class Vector , class SampleBatch >

void shark::TruncatedExponentialLayer::parameterDerivative	(	Vector &	derivative,
		SampleBatch const &	samples
	)		const

inline

Calculates the derivatives of the energy term of this neuron layer with respect to it's parameters - the bias weights.

This function takes a batch of samples and extracts the required informations out of it.

Parameters

derivative	the derivative with respect to the parameters, the result is added on top of it to accumulate derivatives
samples	the sample from which the informations can be extracted

Definition at line 256 of file TruncatedExponentialLayer.h.

References SIZE_CHECK.

◆ parameterVector()

RealVector shark::TruncatedExponentialLayer::parameterVector ( ) const

inlinevirtual

Returns the vector with the parameters associated with the neurons in the layer.

Reimplemented from shark::IParameterizable<>.

Definition at line 262 of file TruncatedExponentialLayer.h.

◆ phi()

template<class Matrix >

Matrix const& shark::TruncatedExponentialLayer::phi ( Matrix const & state ) const

inline

Transforms the current state of the neurons for the multiplication with the weight matrix of the RBM, i.e. calculates the value of the phi-function used in the interaction term.

Parameters

state the state matrix of the neuron layer

Returns: the value of the phi-function

Definition at line 161 of file TruncatedExponentialLayer.h.

References SIZE_CHECK.

◆ read()

void shark::TruncatedExponentialLayer::read ( InArchive & archive )

inlinevirtual

Reads the bias parameters from an archive.

Reimplemented from shark::ISerializable.

Definition at line 277 of file TruncatedExponentialLayer.h.

◆ resize()

void shark::TruncatedExponentialLayer::resize ( std::size_t newSize )

inline

Resizes this neuron layer.

Parameters

newSize number of neurons in the layer

Definition at line 97 of file TruncatedExponentialLayer.h.

◆ sample()

template<class Matrix , class Rng >

void shark::TruncatedExponentialLayer::sample	(	StatisticsBatch const &	statistics,
		Matrix &	state,
		double	alpha,
		Rng &	rng
	)		const

inline

Samples from the truncated exponential distribution using either Gibbs- or flip-the-state sampling given the sufficient statistics (i.e. the parameter lambda and the value of exp(-lambda))

The truncated exponential function is defined as

\[ p(x) = \lambda \frac{e^{-lambdax}}{1 - e^{-\lambda}}\]

with x being in the range of [0,1]

For alpha= 0 gibbs sampling is performed. That is the next state for neuron i is directly taken from the conditional distribution of the i-th neuron. In the case of alpha=1, flip-the-state sampling is performed, which takes the last state into account and tries to do deterministically jump into states with higher probability. THIS IS NOT IMPLEMENTED YET and alpha is ignored!

Parameters

statistics	sufficient statistics for the batch to be computed
state	the state matrix that will hold the sampled states
alpha	factor changing from gibbs to flip-the state sampling. 0<=alpha<=1
rng	the random number generator used for sampling

Definition at line 140 of file TruncatedExponentialLayer.h.

References SHARK_CRITICAL_REGION, SIZE_CHECK, and shark::random::truncExp().

◆ setParameterVector()

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

inlinevirtual

Returns the vector with the parameters associated with the neurons in the layer.

Reimplemented from shark::IParameterizable<>.

Definition at line 267 of file TruncatedExponentialLayer.h.

◆ size()

std::size_t shark::TruncatedExponentialLayer::size ( ) const

inline

Returns the number of neurons of this layer.

Definition at line 102 of file TruncatedExponentialLayer.h.

◆ sufficientStatistics()

template<class Input , class BetaVector >

void shark::TruncatedExponentialLayer::sufficientStatistics	(	Input const &	input,
		StatisticsBatch &	statistics,
		BetaVector const &	beta
	)		const

inline

Takes the input of the neuron and calculates the statistics required to sample from the conditional distribution.

Parameters

input	the batch of inputs of the neuron
statistics	sufficient statistics containing the probabilities of the neurons to be one
beta	the inverse Temperature of the RBM (typically 1) for the whole batch

Definition at line 112 of file TruncatedExponentialLayer.h.

References SIZE_CHECK.

◆ write()

void shark::TruncatedExponentialLayer::write ( OutArchive & archive ) const

inlinevirtual

Writes the bias parameters to an archive.

Reimplemented from shark::ISerializable.

Definition at line 281 of file TruncatedExponentialLayer.h.

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

include/shark/Unsupervised/RBM/Neuronlayers/TruncatedExponentialLayer.h

Public Types

Public Member Functions

Detailed Description

Member Typedef Documentation

◆ StateSpace

◆ StatisticsBatch

◆ SufficientStatistics

Member Function Documentation

◆ bias() [1/2]

◆ bias() [2/2]

◆ energyTerm()

◆ expectedParameterDerivative()

◆ expectedPhiValue()

◆ logMarginalize()

◆ mean()

◆ numberOfParameters()

◆ parameterDerivative()

◆ parameterVector()

◆ phi()

◆ read()

◆ resize()

◆ sample()

◆ setParameterVector()

◆ size()

◆ sufficientStatistics()

◆ write()