|
SHOGUN
4.1.0
|
All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Friends Macros Modules Pages
|
SHOGUN
4.1.0
|
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()
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_t > | get_parameters () |
| virtual SGMatrix< float64_t > | get_weights (SGVector< float64_t > p=SGVector< float64_t >()) |
| virtual SGVector< float64_t > | get_hidden_bias (SGVector< float64_t > p=SGVector< float64_t >()) |
| virtual SGVector< float64_t > | get_visible_bias (SGVector< float64_t > p=SGVector< float64_t >()) |
| virtual int32_t | get_num_parameters () |
| virtual const char * | get_name () const |
| virtual CSGObject * | shallow_copy () const |
| virtual CSGObject * | deep_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) |
| SGIO * | get_global_io () |
| void | set_global_parallel (Parallel *parallel) |
| Parallel * | get_global_parallel () |
| void | set_global_version (Version *version) |
| Version * | get_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) |
| virtual void | update_parameter_hash () |
| virtual bool | parameter_hash_changed () |
| virtual bool | equals (CSGObject *other, float64_t accuracy=0.0, bool tolerant=false) |
| virtual CSGObject * | clone () |
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_t > | hidden_state |
| SGMatrix< float64_t > | visible_state |
| SGIO * | io |
| Parallel * | parallel |
| Version * | version |
| Parameter * | m_parameters |
| Parameter * | m_model_selection_parameters |
| Parameter * | m_gradient_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) |
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_t > | m_params |
Friends | |
| class | CDeepBeliefNetwork |
| CRBM | ( | int32_t | num_hidden | ) |
Constructs an RBM with no visible units. The visible units can be added later using add_visible_group()
| num_hidden | Number of hidden units |
| CRBM | ( | int32_t | num_hidden, |
| int32_t | num_visible, | ||
| ERBMVisibleUnitType | visible_unit_type = RBMVUT_BINARY |
||
| ) |
|
virtual |
|
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.
| dict | dictionary of parameters to be built. |
Definition at line 597 of file SGObject.cpp.
|
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.
Definition at line 714 of file SGObject.cpp.
|
virtual |
Computes the gradients using contrastive divergence
| visible_batch | States of the visible units |
| gradients | Array in which the results are stored. Length get_num_parameters() |
|
virtualinherited |
A deep copy. All the instance variables will also be copied.
Definition at line 198 of file SGObject.cpp.
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.
| other | object to compare with |
| accuracy | accuracy to use for comparison (optional) |
| tolerant | allows linient check on float equality (within accuracy) |
Definition at line 618 of file SGObject.cpp.
|
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):
\[ F(v) = -b^T v - \sum log(1+exp(Wv+c)) \quad \text{for binary visible units}\]
\[ F(v) = \frac{1}{2} v^T v - b^T v - \sum log(1+exp(Wv+c)) \quad \text{for gaussian visible units}\]
| 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. |
|
virtual |
Computes the gradients of the free energy function with respect to the RBM's 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() |
|
inherited |
|
inherited |
|
inherited |
|
inherited |
Definition at line 498 of file SGObject.cpp.
|
inherited |
Returns description of a given parameter string, if it exists. SG_ERROR otherwise
| param_name | name of the parameter |
Definition at line 522 of file SGObject.cpp.
|
inherited |
Returns index of model selection parameter with provided index
| param_name | name of model selection parameter |
Definition at line 535 of file SGObject.cpp.
|
virtual |
|
virtual |
|
virtual |
|
virtualinherited |
If the SGSerializable is a class template then TRUE will be returned and GENERIC is set to the type of the generic.
| generic | set to the type of the generic if returning TRUE |
Definition at line 296 of file SGObject.cpp.
|
virtualinherited |
Load this object from file. If it will fail (returning FALSE) then this object will contain inconsistent data and should not be used!
| file | where to load from |
| prefix | prefix for members |
Definition at line 369 of file SGObject.cpp.
|
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.
| ShogunException | will be thrown if an error occurs. |
Reimplemented in CKernel, CWeightedDegreePositionStringKernel, CList, CAlphabet, CLinearHMM, CGaussianKernel, CInverseMultiQuadricKernel, CCircularKernel, and CExponentialKernel.
Definition at line 426 of file SGObject.cpp.
|
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.
| ShogunException | will be thrown if an error occurs. |
Reimplemented in CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, and CDynamicObjectArray.
Definition at line 421 of file SGObject.cpp.
|
virtualinherited |
Definition at line 262 of file SGObject.cpp.
|
inherited |
prints all parameter registered for model selection and their type
Definition at line 474 of file SGObject.cpp.
|
virtualinherited |
prints registered parameters out
| prefix | prefix for members |
Definition at line 308 of file SGObject.cpp.
|
virtual |
Computes an approximation to the pseudo-likelihood. See this tutorial for more details. Only works with binary visible units
| 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. |
| return | Approximation to the average pseudo-likelihood over the given batch |
|
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
|
virtual |
|
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.
| num_gibbs_steps | Number of Gibbs sampling steps |
| batch_size | Number of samples to be drawn. A seperate chain is used for each sample |
|
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.
| 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 |
|
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.
| 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 |
|
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.
| E | Index of the evidence visible unit group |
| evidence | States of the evidence visible unit group |
| num_gibbs_steps | Number of Gibbs sampling steps |
|
virtualinherited |
Save this object to file.
| file | where to save the object; will be closed during returning if PREFIX is an empty string. |
| prefix | prefix for members |
Definition at line 314 of file SGObject.cpp.
|
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.
| ShogunException | will be thrown if an error occurs. |
Reimplemented in CKernel.
Definition at line 436 of file SGObject.cpp.
|
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.
| ShogunException | will be thrown if an error occurs. |
Reimplemented in CKernel, CDynamicArray< T >, CDynamicArray< float64_t >, CDynamicArray< float32_t >, CDynamicArray< int32_t >, CDynamicArray< char >, CDynamicArray< bool >, and CDynamicObjectArray.
Definition at line 431 of file SGObject.cpp.
|
virtual |
|
inherited |
Definition at line 41 of file SGObject.cpp.
|
inherited |
Definition at line 46 of file SGObject.cpp.
|
inherited |
Definition at line 51 of file SGObject.cpp.
|
inherited |
Definition at line 56 of file SGObject.cpp.
|
inherited |
Definition at line 61 of file SGObject.cpp.
|
inherited |
Definition at line 66 of file SGObject.cpp.
|
inherited |
Definition at line 71 of file SGObject.cpp.
|
inherited |
Definition at line 76 of file SGObject.cpp.
|
inherited |
Definition at line 81 of file SGObject.cpp.
|
inherited |
Definition at line 86 of file SGObject.cpp.
|
inherited |
Definition at line 91 of file SGObject.cpp.
|
inherited |
Definition at line 96 of file SGObject.cpp.
|
inherited |
Definition at line 101 of file SGObject.cpp.
|
inherited |
Definition at line 106 of file SGObject.cpp.
|
inherited |
Definition at line 111 of file SGObject.cpp.
|
inherited |
set generic type to T
|
inherited |
|
inherited |
set the parallel object
| parallel | parallel object to use |
Definition at line 241 of file SGObject.cpp.
|
inherited |
set the version object
| version | version object to use |
Definition at line 283 of file SGObject.cpp.
|
virtualinherited |
A shallow copy. All the SGObject instance variables will be simply assigned and SG_REF-ed.
Reimplemented in CGaussianKernel.
Definition at line 192 of file SGObject.cpp.
|
virtual |
|
inherited |
unset generic type
this has to be called in classes specializing a template class
Definition at line 303 of file SGObject.cpp.
|
virtualinherited |
Updates the hash of current parameter combination
Definition at line 248 of file SGObject.cpp.
|
virtual |
Returns the states of the visible unit as CDenseFeatures<float64_t>
|
friend |
| int32_t cd_num_steps |
| bool cd_persistent |
| bool cd_sample_visible |
| float64_t gd_learning_rate |
| float64_t gd_learning_rate_decay |
| int32_t gd_mini_batch_size |
| float64_t gd_momentum |
|
inherited |
io
Definition at line 369 of file SGObject.h.
| float64_t l1_coefficient |
| float64_t l2_coefficient |
|
inherited |
parameters wrt which we can compute gradients
Definition at line 384 of file SGObject.h.
|
inherited |
Hash of parameter values
Definition at line 387 of file SGObject.h.
|
inherited |
model selection parameters
Definition at line 381 of file SGObject.h.
|
protected |
|
inherited |
parameters
Definition at line 378 of file SGObject.h.
|
protected |
|
protected |
|
protected |
| int32_t max_num_epochs |
| int32_t monitoring_interval |
| ERBMMonitoringMethod monitoring_method |
|
inherited |
parallel
Definition at line 372 of file SGObject.h.
|
inherited |
version
Definition at line 375 of file SGObject.h.