SHOGUN  4.2.0
CRBM Class Reference

## Detailed Description

A Restricted Boltzmann Machine.

An RBM is an energy based probabilistic model. It consists of two groups of variables: the visible variables $$v$$ and the hidden variables $$h$$. The key assumption that RBMs make is that the hidden units are conditionally independent given the visible units, and vice versa.

The energy function for RBMs with binary visible units is defined as:

$E(v,h) = - b^T v - c^T h - h^T Wv$

and for RBMs with gaussian (linear) visible units:

$E(v,h) = v^T v - b^T v - c^T h - h^T Wv$

where $$b$$ is the bias vector for the visible units, $$c$$ is the bias vector for the hidden units, and $$W$$ is the weight matrix.

The probability distribution is defined through the energy fucntion as:

$P(v,h) = \frac{exp(-E(v,h))}{\sum_{v,h} exp(-E(v,h))}$

The above definitions along with the independence assumptions result in the following conditionals:

$P(h=1|v) = \frac{1}{1+exp(-Wv-c)} \quad \text{for binary hidden units}$

$P(v=1|h) = \frac{1}{1+exp(-W^T h-b)} \quad \text{for binary visible units}$

$P(v|h) \sim \mathcal{N} (W^T h + b,1) \quad \text{for gaussian visible units}$

Note that when using gaussian visible units, the inputs should be normalized to have zero mean and unity standard deviation.

This class supports having multiple types of visible units in the same RBM. The visible units are divided into groups where each group can have its own type. The hidden units however are just one group of binary units.

Samples can be drawn from the model using Gibbs sampling.

Training is done using contrastive divergence [Hinton, 2002] or persistent contrastive divergence [Tieleman, 2008] (default).

Training progress can be monitored using the reconstruction error (default), which is the average squared difference between a training batch and the RBM's reconstruction of it. The reconstruction is generated using one step of gibbs sampling. Progress can also be monitored using the pseudo-log-likelihood which is an approximation to the log-likelihood. However, this is currently only supported for binary visible units.

The rows of the visible_state matrix are divided into groups, one for each group of visible units. For example, if we have 3 groups of visible units: group 0 with 10 units, group 1 with 5 units, and group 2 with 6 units, the states of group 0 will be stored in visible_state[0:10,:], the states of group 1 will stored in visible_state[10:15,:], and the states of group 2 will be stored in visible_state[15:21,:]. Note that the groups are numbered by the order in which they where added to the RBM using add_visible_group()

Definition at line 122 of file RBM.h.

Inheritance diagram for CRBM:
[legend]

## Public Member Functions

CRBM ()

CRBM (int32_t num_hidden)

CRBM (int32_t num_hidden, int32_t num_visible, ERBMVisibleUnitType visible_unit_type=RBMVUT_BINARY)

virtual ~CRBM ()

virtual void add_visible_group (int32_t num_units, ERBMVisibleUnitType unit_type)

virtual void initialize_neural_network (float64_t sigma=0.01)

virtual void set_batch_size (int32_t batch_size)

virtual void train (CDenseFeatures< float64_t > *features)

virtual void sample (int32_t num_gibbs_steps=1, int32_t batch_size=1)

virtual CDenseFeatures
< float64_t > *
sample_group (int32_t V, int32_t num_gibbs_steps=1, int32_t batch_size=1)

virtual void sample_with_evidence (int32_t E, CDenseFeatures< float64_t > *evidence, int32_t num_gibbs_steps=1)

virtual CDenseFeatures
< float64_t > *
sample_group_with_evidence (int32_t V, int32_t E, CDenseFeatures< float64_t > *evidence, int32_t num_gibbs_steps=1)

virtual void reset_chain ()

virtual float64_t free_energy (SGMatrix< float64_t > visible, SGMatrix< float64_t > buffer=SGMatrix< float64_t >())

virtual void free_energy_gradients (SGMatrix< float64_t > visible, SGVector< float64_t > gradients, bool positive_phase=true, SGMatrix< float64_t > hidden_mean_given_visible=SGMatrix< float64_t >())

virtual void contrastive_divergence (SGMatrix< float64_t > visible_batch, SGVector< float64_t > gradients)

virtual float64_t reconstruction_error (SGMatrix< float64_t > visible, SGMatrix< float64_t > buffer=SGMatrix< float64_t >())

virtual float64_t pseudo_likelihood (SGMatrix< float64_t > visible, SGMatrix< float64_t > buffer=SGMatrix< float64_t >())

virtual CDenseFeatures
< float64_t > *
visible_state_features ()

virtual SGVector< float64_tget_parameters ()

virtual SGMatrix< float64_tget_weights (SGVector< float64_t > p=SGVector< float64_t >())

virtual SGVector< float64_tget_hidden_bias (SGVector< float64_t > p=SGVector< float64_t >())

virtual SGVector< float64_tget_visible_bias (SGVector< float64_t > p=SGVector< float64_t >())

virtual int32_t get_num_parameters ()

virtual const char * get_name () const

virtual CSGObjectshallow_copy () const

virtual CSGObjectdeep_copy () const

virtual bool is_generic (EPrimitiveType *generic) const

template<class T >
void set_generic ()

template<>
void set_generic ()

template<>
void set_generic ()

template<>
void set_generic ()

template<>
void set_generic ()

template<>
void set_generic ()

template<>
void set_generic ()

template<>
void set_generic ()

template<>
void set_generic ()

template<>
void set_generic ()

template<>
void set_generic ()

template<>
void set_generic ()

template<>
void set_generic ()

template<>
void set_generic ()

template<>
void set_generic ()

template<>
void set_generic ()

void unset_generic ()

virtual void print_serializable (const char *prefix="")

virtual bool save_serializable (CSerializableFile *file, const char *prefix="")

virtual bool load_serializable (CSerializableFile *file, const char *prefix="")

void set_global_io (SGIO *io)

SGIOget_global_io ()

void set_global_parallel (Parallel *parallel)

Parallelget_global_parallel ()

void set_global_version (Version *version)

Versionget_global_version ()

SGStringList< char > get_modelsel_names ()

void print_modsel_params ()

char * get_modsel_param_descr (const char *param_name)

index_t get_modsel_param_index (const char *param_name)

void build_gradient_parameter_dictionary (CMap< TParameter *, CSGObject * > *dict)

bool has (const std::string &name) const

template<typename T >
bool has (const Tag< T > &tag) const

template<typename T , typename U = void>
bool has (const std::string &name) const

template<typename T >
void set (const Tag< T > &_tag, const T &value)

template<typename T , typename U = void>
void set (const std::string &name, const T &value)

template<typename T >
get (const Tag< T > &_tag) const

template<typename T , typename U = void>
get (const std::string &name) const

virtual void update_parameter_hash ()

virtual bool parameter_hash_changed ()

virtual bool equals (CSGObject *other, float64_t accuracy=0.0, bool tolerant=false)

virtual CSGObjectclone ()

## Public Attributes

int32_t cd_num_steps

bool cd_persistent

bool cd_sample_visible

float64_t l2_coefficient

float64_t l1_coefficient

int32_t monitoring_interval

ERBMMonitoringMethod monitoring_method

int32_t max_num_epochs

int32_t gd_mini_batch_size

float64_t gd_learning_rate

float64_t gd_learning_rate_decay

float64_t gd_momentum

SGMatrix< float64_thidden_state

SGMatrix< float64_tvisible_state

SGIOio

Parallelparallel

Versionversion

Parameterm_parameters

Parameterm_model_selection_parameters

uint32_t m_hash

## Protected Member Functions

virtual void mean_hidden (SGMatrix< float64_t > visible, SGMatrix< float64_t > result)

virtual void mean_visible (SGMatrix< float64_t > hidden, SGMatrix< float64_t > result)

virtual void sample_hidden (SGMatrix< float64_t > mean, SGMatrix< float64_t > result)

virtual void sample_visible (SGMatrix< float64_t > mean, SGMatrix< float64_t > result)

virtual void sample_visible (int32_t index, SGMatrix< float64_t > mean, SGMatrix< float64_t > result)

virtual void load_serializable_pre () throw (ShogunException)

virtual void load_serializable_post () throw (ShogunException)

virtual void save_serializable_pre () throw (ShogunException)

virtual void save_serializable_post () throw (ShogunException)

template<typename T >
void register_param (Tag< T > &_tag, const T &value)

template<typename T >
void register_param (const std::string &name, const T &value)

## Protected Attributes

int32_t m_num_hidden

int32_t m_num_visible

int32_t m_batch_size

int32_t m_num_visible_groups

CDynamicArray< int32_t > * m_visible_group_types

CDynamicArray< int32_t > * m_visible_group_sizes

CDynamicArray< int32_t > * m_visible_state_offsets

int32_t m_num_params

SGVector< float64_tm_params

## Friends

class CDeepBeliefNetwork

## Constructor & Destructor Documentation

 CRBM ( )

default constructor

Definition at line 43 of file RBM.cpp.

 CRBM ( int32_t num_hidden )

Constructs an RBM with no visible units. The visible units can be added later using add_visible_group()

Parameters
 num_hidden Number of hidden units

Definition at line 48 of file RBM.cpp.

 CRBM ( int32_t num_hidden, int32_t num_visible, ERBMVisibleUnitType visible_unit_type = RBMVUT_BINARY )

Constructs an RBM with a single group of visible units

Parameters
 num_hidden Number of hidden units num_visible Number of visible units visible_unit_type Type of the visible units

Definition at line 54 of file RBM.cpp.

 ~CRBM ( )
virtual

Definition at line 62 of file RBM.cpp.

## Member Function Documentation

 void add_visible_group ( int32_t num_units, ERBMVisibleUnitType unit_type )
virtual

Adds a group of visible units to the RBM

Parameters
 num_units Number of visible units unit_type Type of the visible units

Definition at line 69 of file RBM.cpp.

 void build_gradient_parameter_dictionary ( CMap< TParameter *, CSGObject * > * dict )
inherited

Builds a dictionary of all parameters in SGObject as well of those of SGObjects that are parameters of this object. Dictionary maps parameters to the objects that own them.

Parameters
 dict dictionary of parameters to be built.

Definition at line 630 of file SGObject.cpp.

 CSGObject * clone ( )
virtualinherited

Creates a clone of the current object. This is done via recursively traversing all parameters, which corresponds to a deep copy. Calling equals on the cloned object always returns true although none of the memory of both objects overlaps.

Returns
an identical copy of the given object, which is disjoint in memory. NULL if the clone fails. Note that the returned object is SG_REF'ed

Definition at line 747 of file SGObject.cpp.

 void contrastive_divergence ( SGMatrix< float64_t > visible_batch, SGVector< float64_t > gradients )
virtual

Computes the gradients using contrastive divergence

Parameters
 visible_batch States of the visible units gradients Array in which the results are stored. Length get_num_parameters()

Definition at line 355 of file RBM.cpp.

 CSGObject * deep_copy ( ) const
virtualinherited

A deep copy. All the instance variables will also be copied.

Definition at line 231 of file SGObject.cpp.

 bool equals ( CSGObject * other, float64_t accuracy = 0.0, bool tolerant = false )
virtualinherited

Recursively compares the current SGObject to another one. Compares all registered numerical parameters, recursion upon complex (SGObject) parameters. Does not compare pointers!

May be overwritten but please do with care! Should not be necessary in most cases.

Parameters
 other object to compare with accuracy accuracy to use for comparison (optional) tolerant allows linient check on float equality (within accuracy)
Returns
true if all parameters were equal, false if not

Definition at line 651 of file SGObject.cpp.

 float64_t free_energy ( SGMatrix< float64_t > visible, SGMatrix< float64_t > buffer = SGMatrix() )
virtual

Computes the average free energy on a given batch of visible unit states.

The free energy for a vector $$v$$ is defined as:

$F(v) = - log(\sum_h exp(-E(v,h))$

which yields the following (in vectorized form):

$F(v) = -b^T v - \sum log(1+exp(Wv+c)) \quad \text{for binary visible units}$

$F(v) = \frac{1}{2} v^T v - b^T v - \sum log(1+exp(Wv+c)) \quad \text{for gaussian visible units}$

Parameters
 visible States of the visible units buffer A matrix of size num_hidden*batch_size. used as a buffer during computation. If not given, a new matrix is allocated and used as a buffer.
Returns
Average free energy over the given batch

Definition at line 272 of file RBM.cpp.

 void free_energy_gradients ( SGMatrix< float64_t > visible, SGVector< float64_t > gradients, bool positive_phase = true, SGMatrix< float64_t > hidden_mean_given_visible = SGMatrix() )
virtual

Computes the gradients of the free energy function with respect to the RBM's parameters

Parameters
 visible States of the visible units gradients Array in which the results are stored. Length get_num_parameters() positive_phase If true, the result vector is reset to zero and the gradients are added to it with a positive sign. If false, the result vector is not reset and the gradients are added to it with a negative sign. This is useful during contrastive divergence. hidden_mean_given_visible Means of the hidden states given the visible states. If not given, means will be computed by calling mean_hidden()

Definition at line 318 of file RBM.cpp.

 T get ( const Tag< T > & _tag ) const
inherited

Getter for a class parameter, identified by a Tag. Throws an exception if the class does not have such a parameter.

Parameters
 _tag name and type information of parameter
Returns
value of the parameter identified by the input tag

Definition at line 367 of file SGObject.h.

 T get ( const std::string & name ) const
inherited

Getter for a class parameter, identified by a name. Throws an exception if the class does not have such a parameter.

Parameters
 name name of the parameter
Returns
value of the parameter corresponding to the input name and type

Definition at line 388 of file SGObject.h.

 SGIO * get_global_io ( )
inherited

get the io object

Returns
io object

Definition at line 268 of file SGObject.cpp.

 Parallel * get_global_parallel ( )
inherited

get the parallel object

Returns
parallel object

Definition at line 310 of file SGObject.cpp.

 Version * get_global_version ( )
inherited

get the version object

Returns
version object

Definition at line 323 of file SGObject.cpp.

 SGVector< float64_t > get_hidden_bias ( SGVector< float64_t > p = SGVector() )
virtual

Returns the bias vector of the hidden units

Parameters
 p If specified, the bias vector is extracted from it instead of m_params

Definition at line 580 of file RBM.cpp.

 SGStringList< char > get_modelsel_names ( )
inherited
Returns
vector of names of all parameters which are registered for model selection

Definition at line 531 of file SGObject.cpp.

 char * get_modsel_param_descr ( const char * param_name )
inherited

Returns description of a given parameter string, if it exists. SG_ERROR otherwise

Parameters
 param_name name of the parameter
Returns
description of the parameter

Definition at line 555 of file SGObject.cpp.

 index_t get_modsel_param_index ( const char * param_name )
inherited

Returns index of model selection parameter with provided index

Parameters
 param_name name of model selection parameter
Returns
index of model selection parameter with provided name, -1 if there is no such

Definition at line 568 of file SGObject.cpp.

 virtual const char* get_name ( ) const
virtual

Returns the name of the SGSerializable instance. It MUST BE the CLASS NAME without the prefixed C'.

Returns
name of the SGSerializable

Implements CSGObject.

Definition at line 346 of file RBM.h.

 virtual int32_t get_num_parameters ( )
virtual

Returns the number of parameters

Definition at line 344 of file RBM.h.

 virtual SGVector get_parameters ( )
virtual

Returns the parameter vector of the RBM

Definition at line 317 of file RBM.h.

 SGVector< float64_t > get_visible_bias ( SGVector< float64_t > p = SGVector() )
virtual

Returns the bias vector of the visible units

Parameters
 p If specified, the bias vector is extracted from it instead of m_params

Definition at line 590 of file RBM.cpp.

 SGMatrix< float64_t > get_weights ( SGVector< float64_t > p = SGVector() )
virtual

Returns the weights matrix

Parameters
 p If specified, the weight matrix is extracted from it instead of m_params

Definition at line 570 of file RBM.cpp.

 bool has ( const std::string & name ) const
inherited

Checks if object has a class parameter identified by a name.

Parameters
 name name of the parameter
Returns
true if the parameter exists with the input name

Definition at line 289 of file SGObject.h.

 bool has ( const Tag< T > & tag ) const
inherited

Checks if object has a class parameter identified by a Tag.

Parameters
 tag tag of the parameter containing name and type information
Returns
true if the parameter exists with the input tag

Definition at line 301 of file SGObject.h.

 bool has ( const std::string & name ) const
inherited

Checks if a type exists for a class parameter identified by a name.

Parameters
 name name of the parameter
Returns
true if the parameter exists with the input name and type

Definition at line 312 of file SGObject.h.

 void initialize_neural_network ( float64_t sigma = 0.01 )
virtual

Initializes the weights of the RBM. Must be called after all the visible groups have been added, and before the RBM is used.

Parameters
 sigma Standard deviation of the gaussian used to initialize the weights

Definition at line 86 of file RBM.cpp.

 bool is_generic ( EPrimitiveType * generic ) const
virtualinherited

If the SGSerializable is a class template then TRUE will be returned and GENERIC is set to the type of the generic.

Parameters
 generic set to the type of the generic if returning TRUE
Returns
TRUE if a class template.

Definition at line 329 of file SGObject.cpp.

 bool load_serializable ( CSerializableFile * file, const char * prefix = "" )
virtualinherited

Load this object from file. If it will fail (returning FALSE) then this object will contain inconsistent data and should not be used!

Parameters
 file where to load from prefix prefix for members
Returns
TRUE if done, otherwise FALSE

Definition at line 402 of file SGObject.cpp.

 void load_serializable_post ( ) throw ( ShogunException )
protectedvirtualinherited

Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_POST is called.

Exceptions
 ShogunException will be thrown if an error occurs.

Definition at line 459 of file SGObject.cpp.

 void load_serializable_pre ( ) throw ( ShogunException )
protectedvirtualinherited

Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::LOAD_SERIALIZABLE_PRE is called.

Exceptions
 ShogunException will be thrown if an error occurs.

Definition at line 454 of file SGObject.cpp.

 void mean_hidden ( SGMatrix< float64_t > visible, SGMatrix< float64_t > result )
protectedvirtual

Computes the mean of the hidden states given the visible states

Definition at line 450 of file RBM.cpp.

 void mean_visible ( SGMatrix< float64_t > hidden, SGMatrix< float64_t > result )
protectedvirtual

Computes the mean of the visible states given the hidden states

Definition at line 468 of file RBM.cpp.

 bool parameter_hash_changed ( )
virtualinherited
Returns
whether parameter combination has changed since last update

Definition at line 295 of file SGObject.cpp.

 void print_modsel_params ( )
inherited

prints all parameter registered for model selection and their type

Definition at line 507 of file SGObject.cpp.

 void print_serializable ( const char * prefix = "" )
virtualinherited

prints registered parameters out

Parameters
 prefix prefix for members

Definition at line 341 of file SGObject.cpp.

 float64_t pseudo_likelihood ( SGMatrix< float64_t > visible, SGMatrix< float64_t > buffer = SGMatrix() )
virtual

Computes an approximation to the pseudo-likelihood. See this tutorial for more details. Only works with binary visible units

Parameters
 visible States of the visible units buffer A matrix of size num_visible*batch_size. used as a buffer during computation. If not given, a new matrix is allocated and used as a buffer.
Returns
Approximation to the average pseudo-likelihood over the given batch

Definition at line 420 of file RBM.cpp.

 float64_t reconstruction_error ( SGMatrix< float64_t > visible, SGMatrix< float64_t > buffer = SGMatrix() )
virtual

Computes the average reconstruction error which is defined as:

$E = \frac{1}{N} \sum_i (v_i - \widetilde{v})^2$

where $$\widetilde{v}$$ is computed using one step of gibbs sampling and $$N$$ is the batch size

Returns
Average reconstruction error over the given batch

Definition at line 398 of file RBM.cpp.

 void register_param ( Tag< T > & _tag, const T & value )
protectedinherited

Registers a class parameter which is identified by a tag. This enables the parameter to be modified by set() and retrieved by get(). Parameters can be registered in the constructor of the class.

Parameters
 _tag name and type information of parameter value value of the parameter

Definition at line 439 of file SGObject.h.

 void register_param ( const std::string & name, const T & value )
protectedinherited

Registers a class parameter which is identified by a name. This enables the parameter to be modified by set() and retrieved by get(). Parameters can be registered in the constructor of the class.

Parameters
 name name of the parameter value value of the parameter along with type information

Definition at line 452 of file SGObject.h.

 void reset_chain ( )
virtual

Resets the state of the markov chain used for sampling, which is stored in the visible_state matrix, to random values

Definition at line 265 of file RBM.cpp.

 void sample ( int32_t num_gibbs_steps = 1, int32_t batch_size = 1 )
virtual

Draws samples from the marginal distribution of the visible units using Gibbs sampling. The sampling starts from the values in the RBM's visible_state matrix and result of the sampling is stored there too.

Parameters
 num_gibbs_steps Number of Gibbs sampling steps batch_size Number of samples to be drawn. A seperate chain is used for each sample

Definition at line 178 of file RBM.cpp.

 CDenseFeatures< float64_t > * sample_group ( int32_t V, int32_t num_gibbs_steps = 1, int32_t batch_size = 1 )
virtual

Draws Samples from $$P(V)$$ where $$V$$ is one of the visible unit groups. The sampling starts from the values in the RBM's visible_state matrix and result of the sampling is stored there too.

Parameters
 V Index of the visible unit group to be sampled num_gibbs_steps Number of Gibbs sampling steps batch_size Number of samples to be drawn. A seperate chain is used for each sample
Returns
Sampled states of group V

Definition at line 193 of file RBM.cpp.

 CDenseFeatures< float64_t > * sample_group_with_evidence ( int32_t V, int32_t E, CDenseFeatures< float64_t > * evidence, int32_t num_gibbs_steps = 1 )
virtual

Draws Samples from $$P(V|E=evidence)$$ where $$E$$ is one of the visible unit groups and $$V$$ is another visible unit group. The sampling starts from the values in the RBM's visible_state matrix and result of the sampling is stored there too.

Parameters
 V Index of the visible unit group to be sampled E Index of the evidence visible unit group evidence States of the evidence visible unit group num_gibbs_steps Number of Gibbs sampling steps
Returns
Sampled states of group V

Definition at line 245 of file RBM.cpp.

 void sample_hidden ( SGMatrix< float64_t > mean, SGMatrix< float64_t > result )
protectedvirtual

Samples the hidden states according to the provided means

Definition at line 519 of file RBM.cpp.

 void sample_visible ( SGMatrix< float64_t > mean, SGMatrix< float64_t > result )
protectedvirtual

Samples the visible states according to the provided means

Definition at line 526 of file RBM.cpp.

 void sample_visible ( int32_t index, SGMatrix< float64_t > mean, SGMatrix< float64_t > result )
protectedvirtual

Samples one group of visible states according to the provided means

Definition at line 534 of file RBM.cpp.

 void sample_with_evidence ( int32_t E, CDenseFeatures< float64_t > * evidence, int32_t num_gibbs_steps = 1 )
virtual

Draws Samples from $$P(V|E=evidence)$$ where $$E$$ is one of the visible unit groups and $$V$$ is all the visible unit excluding the ones in group $$E$$. The sampling starts from the values in the RBM's visible_state matrix and result of the sampling is stored there too.

Parameters
 E Index of the evidence visible unit group evidence States of the evidence visible unit group num_gibbs_steps Number of Gibbs sampling steps

Definition at line 211 of file RBM.cpp.

 bool save_serializable ( CSerializableFile * file, const char * prefix = ""` )
virtualinherited

Save this object to file.

Parameters
 file where to save the object; will be closed during returning if PREFIX is an empty string. prefix prefix for members
Returns
TRUE if done, otherwise FALSE

Definition at line 347 of file SGObject.cpp.

 void save_serializable_post ( ) throw ( ShogunException )
protectedvirtualinherited

Can (optionally) be overridden to post-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_POST is called.

Exceptions
 ShogunException will be thrown if an error occurs.

Reimplemented in CKernel.

Definition at line 469 of file SGObject.cpp.

 void save_serializable_pre ( ) throw ( ShogunException )
protectedvirtualinherited

Can (optionally) be overridden to pre-initialize some member variables which are not PARAMETER::ADD'ed. Make sure that at first the overridden method BASE_CLASS::SAVE_SERIALIZABLE_PRE is called.

Exceptions
 ShogunException will be thrown if an error occurs.

Definition at line 464 of file SGObject.cpp.

 void set ( const Tag< T > & _tag, const T & value )
inherited

Setter for a class parameter, identified by a Tag. Throws an exception if the class does not have such a parameter.

Parameters
 _tag name and type information of parameter value value of the parameter

Definition at line 328 of file SGObject.h.

 void set ( const std::string & name, const T & value )
inherited

Setter for a class parameter, identified by a name. Throws an exception if the class does not have such a parameter.

Parameters
 name name of the parameter value value of the parameter along with type information

Definition at line 354 of file SGObject.h.

 void set_batch_size ( int32_t batch_size )
virtual

Sets the number of train/test cases the RBM will deal with

Parameters
 batch_size Batch size

Definition at line 95 of file RBM.cpp.

 void set_generic ( )
inherited

Definition at line 74 of file SGObject.cpp.

 void set_generic ( )
inherited

Definition at line 79 of file SGObject.cpp.

 void set_generic ( )
inherited

Definition at line 84 of file SGObject.cpp.

 void set_generic ( )
inherited

Definition at line 89 of file SGObject.cpp.

 void set_generic ( )
inherited

Definition at line 94 of file SGObject.cpp.

 void set_generic ( )
inherited

Definition at line 99 of file SGObject.cpp.

 void set_generic ( )
inherited

Definition at line 104 of file SGObject.cpp.

 void set_generic ( )
inherited

Definition at line 109 of file SGObject.cpp.

 void set_generic ( )
inherited

Definition at line 114 of file SGObject.cpp.

 void set_generic ( )
inherited

Definition at line 119 of file SGObject.cpp.

 void set_generic ( )
inherited

Definition at line 124 of file SGObject.cpp.

 void set_generic ( )
inherited

Definition at line 129 of file SGObject.cpp.

 void set_generic ( )
inherited

Definition at line 134 of file SGObject.cpp.

 void set_generic ( )
inherited

Definition at line 139 of file SGObject.cpp.

 void set_generic ( )
inherited

Definition at line 144 of file SGObject.cpp.

 void set_generic ( )
inherited

set generic type to T

 void set_global_io ( SGIO * io )
inherited

set the io object

Parameters
 io io object to use

Definition at line 261 of file SGObject.cpp.

 void set_global_parallel ( Parallel * parallel )
inherited

set the parallel object

Parameters
 parallel parallel object to use

Definition at line 274 of file SGObject.cpp.

 void set_global_version ( Version * version )
inherited

set the version object

Parameters
 version version object to use

Definition at line 316 of file SGObject.cpp.

 CSGObject * shallow_copy ( ) const
virtualinherited

A shallow copy. All the SGObject instance variables will be simply assigned and SG_REF-ed.

Reimplemented in CGaussianKernel.

Definition at line 225 of file SGObject.cpp.

 void train ( CDenseFeatures< float64_t > * features )
virtual

Trains the RBM

Parameters
 features Input features. Should have as many features as there are visible units in the RBM.

Definition at line 107 of file RBM.cpp.

 void unset_generic ( )
inherited

unset generic type

this has to be called in classes specializing a template class

Definition at line 336 of file SGObject.cpp.

 void update_parameter_hash ( )
virtualinherited

Updates the hash of current parameter combination

Definition at line 281 of file SGObject.cpp.

 virtual CDenseFeatures* visible_state_features ( )
virtual

Returns the states of the visible unit as CDenseFeatures<float64_t>

Definition at line 311 of file RBM.h.

## Friends And Related Function Documentation

 friend class CDeepBeliefNetwork
friend

Definition at line 124 of file RBM.h.

## Member Data Documentation

 int32_t cd_num_steps

Number of Gibbs sampling steps performed before each weight update during training. Default value is 1.

Definition at line 372 of file RBM.h.

 bool cd_persistent

If true, persistent contrastive divergence is used. Default value is true.

Definition at line 376 of file RBM.h.

 bool cd_sample_visible

If true, the visible units are sampled during contrastive divergence. If false, the visible units are not sampled, and their mean values are used instead. Default value is false

Definition at line 382 of file RBM.h.

 float64_t gd_learning_rate

gradient descent learning rate, defualt value 0.1

Definition at line 410 of file RBM.h.

 float64_t gd_learning_rate_decay

gradient descent learning rate decay learning rate is updated at each iteration i according to: alpha(i)=decay*alpha(i-1) default value is 1.0 (no decay)

Definition at line 417 of file RBM.h.

 int32_t gd_mini_batch_size

size of the mini-batch used during gradient descent training, if 0 full-batch training is performed default value is 0

Definition at line 407 of file RBM.h.

 float64_t gd_momentum

gradient descent momentum multiplier

default value is 0.9

For more details on momentum, see this paper [Sutskever, 2013]

Definition at line 427 of file RBM.h.

 SGMatrix hidden_state

States of the hidden units

Definition at line 430 of file RBM.h.

 SGIO* io
inherited

io

Definition at line 537 of file SGObject.h.

 float64_t l1_coefficient

L1 Regularization coeff, default value is 0.0

Definition at line 388 of file RBM.h.

 float64_t l2_coefficient

L2 Regularization coeff, default value is 0.0

Definition at line 385 of file RBM.h.

 int32_t m_batch_size
protected

Batch size

Definition at line 443 of file RBM.h.

inherited

parameters wrt which we can compute gradients

Definition at line 552 of file SGObject.h.

 uint32_t m_hash
inherited

Hash of parameter values

Definition at line 555 of file SGObject.h.

 Parameter* m_model_selection_parameters
inherited

model selection parameters

Definition at line 549 of file SGObject.h.

 int32_t m_num_hidden
protected

Number of hidden units

Definition at line 437 of file RBM.h.

 int32_t m_num_params
protected

Number of parameters

Definition at line 458 of file RBM.h.

 int32_t m_num_visible
protected

Number of visible units

Definition at line 440 of file RBM.h.

 int32_t m_num_visible_groups
protected

Number of visible unit groups

Definition at line 446 of file RBM.h.

 Parameter* m_parameters
inherited

parameters

Definition at line 546 of file SGObject.h.

 SGVector m_params
protected

Parameters

Definition at line 461 of file RBM.h.

 CDynamicArray* m_visible_group_sizes
protected

Size of each visible unit group

Definition at line 452 of file RBM.h.

 CDynamicArray* m_visible_group_types
protected

Type of each visible unit group

Definition at line 449 of file RBM.h.

 CDynamicArray* m_visible_state_offsets
protected

Row offsets for accessing the states of each visible unit groups

Definition at line 455 of file RBM.h.

 int32_t max_num_epochs

maximum number of iterations over the training set. defualt value is 1

Definition at line 401 of file RBM.h.

 int32_t monitoring_interval

Number of weight updates between each evaluation of the monitoring method. Default value is 10.

Definition at line 393 of file RBM.h.

 ERBMMonitoringMethod monitoring_method

Monitoring method

Definition at line 396 of file RBM.h.

 Parallel* parallel
inherited

parallel

Definition at line 540 of file SGObject.h.

 Version* version
inherited

version

Definition at line 543 of file SGObject.h.

 SGMatrix visible_state

States of the visible units

Definition at line 433 of file RBM.h.

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

SHOGUN Machine Learning Toolbox - Documentation