SHOGUN  6.1.3
CNeuralLayer Class Reference

## Detailed Description

Base class for neural network layers.

A Neural layer represents an group of neurons and is the basic building block for neural networks.

This class is to be inherited from to implement layers with different neuron types (i.e linear, softmax, convolutional, etc..)

Any arbitrary layer type can be derived from this class provided that the following functions have been defined in a mathematically plausible manner:

The memory for the layer's parameters (weights and biases) is not allocated by the layer itself, instead it is allocated by the network that the layer belongs to, and passed to the layer when it needs to use it.

This class stores buffers for use during forward and backpropagation, this is to avoid unnecessary memory allocation during computations. The buffers are: m_activations: size m_num_neurons*m_batch_size m_activation_gradients: size m_num_neurons*m_batch_size m_local_gradients: size m_num_neurons*m_batch_size

Definition at line 87 of file NeuralLayer.h.

Inheritance diagram for CNeuralLayer:
[legend]

## Public Types

typedef rxcpp::subjects::subject< ObservedValueSGSubject

typedef rxcpp::observable< ObservedValue, rxcpp::dynamic_observable< ObservedValue > > SGObservable

typedef rxcpp::subscriber< ObservedValue, rxcpp::observer< ObservedValue, void, void, void, void > > SGSubscriber

## Public Member Functions

CNeuralLayer ()

CNeuralLayer (int32_t num_neurons)

virtual ~CNeuralLayer ()

virtual void initialize_neural_layer (CDynamicObjectArray *layers, SGVector< int32_t > input_indices)

virtual void set_batch_size (int32_t batch_size)

virtual bool is_input ()

virtual void initialize_parameters (SGVector< float64_t > parameters, SGVector< bool > parameter_regularizable, float64_t sigma)

virtual void compute_activations (SGMatrix< float64_t > inputs)

virtual void compute_activations (SGVector< float64_t > parameters, CDynamicObjectArray *layers)

virtual void compute_gradients (SGVector< float64_t > parameters, SGMatrix< float64_t > targets, CDynamicObjectArray *layers, SGVector< float64_t > parameter_gradients)

virtual float64_t compute_error (SGMatrix< float64_t > targets)

virtual void enforce_max_norm (SGVector< float64_t > parameters, float64_t max_norm)

virtual void dropout_activations ()

virtual float64_t compute_contraction_term (SGVector< float64_t > parameters)

virtual int32_t get_num_neurons ()

virtual int32_t get_width ()

virtual int32_t get_height ()

virtual void set_num_neurons (int32_t num_neurons)

virtual int32_t get_num_parameters ()

virtual SGMatrix< float64_tget_activations ()

virtual SGVector< int32_t > get_input_indices ()

virtual const char * get_name () const

int32_t ref ()

int32_t ref_count ()

int32_t unref ()

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

SGObservableget_parameters_observable ()

void subscribe_to_parameters (ParameterObserverInterface *obs)

void list_observable_parameters ()

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

bool is_training

float64_t dropout_prop

float64_t contraction_coefficient

ENLAutoencoderPosition autoencoder_position

SGIOio

Parallelparallel

Versionversion

Parameterm_parameters

Parameterm_model_selection_parameters

uint32_t m_hash

## Protected Member Functions

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)

bool clone_parameters (CSGObject *other)

void observe (const ObservedValue value)

void register_observable_param (const std::string &name, const SG_OBS_VALUE_TYPE type, const std::string &description)

## Protected Attributes

int32_t m_num_neurons

int32_t m_width

int32_t m_height

int32_t m_num_parameters

SGVector< int32_t > m_input_indices

SGVector< int32_t > m_input_sizes

int32_t m_batch_size

SGMatrix< float64_tm_activations

## ◆ SGObservable

 inherited

Definition at line 130 of file SGObject.h.

## ◆ SGSubject

 inherited

Definition at line 127 of file SGObject.h.

## ◆ SGSubscriber

 typedef rxcpp::subscriber< ObservedValue, rxcpp::observer > SGSubscriber
inherited

Definition at line 133 of file SGObject.h.

## ◆ CNeuralLayer() [1/2]

 CNeuralLayer ( )

default constructor

Definition at line 41 of file NeuralLayer.cpp.

## ◆ CNeuralLayer() [2/2]

 CNeuralLayer ( int32_t num_neurons )

Constuctor

Parameters
 num_neurons Number of neurons in this layer

Definition at line 48 of file NeuralLayer.cpp.

## ◆ ~CNeuralLayer()

 ~CNeuralLayer ( )
virtual

Definition at line 57 of file NeuralLayer.cpp.

## Member Function Documentation

 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 635 of file SGObject.cpp.

## ◆ clone()

 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 734 of file SGObject.cpp.

## ◆ clone_parameters()

 bool clone_parameters ( CSGObject * other )
protectedinherited

Definition at line 759 of file SGObject.cpp.

## ◆ compute_activations() [1/2]

 virtual void compute_activations ( SGMatrix< float64_t > inputs )
virtual

Computes the activations of the neurons in this layer, results should be stored in m_activations. To be used only with input layers

Parameters
 inputs activations of the neurons in the previous layer, matrix of size previous_layer_num_neurons * batch_size

Reimplemented in CNeuralInputLayer.

Definition at line 153 of file NeuralLayer.h.

## ◆ compute_activations() [2/2]

 virtual void compute_activations ( SGVector< float64_t > parameters, CDynamicObjectArray * layers )
virtual

Computes the activations of the neurons in this layer, results should be stored in m_activations. To be used only with non-input layers

Parameters
 parameters Vector of size get_num_parameters(), contains the parameters of the layer layers Array of layers that form the network that this layer is being used with

Definition at line 164 of file NeuralLayer.h.

## ◆ compute_contraction_term()

 virtual float64_t compute_contraction_term ( SGVector< float64_t > parameters )
virtual

Computes

$\frac{\lambda}{N} \sum_{k=0}^{N-1} \left \| J(x_k) \right \|^2_F$

where $$\left \| J(x_k)) \right \|^2_F$$ is the Frobenius norm of the Jacobian of the activations of the hidden layer with respect to its inputs, $$N$$ is the batch size, and $$\lambda$$ is the contraction coefficient.

Should be implemented by layers that support being used as a hidden layer in a contractive autoencoder.

Parameters
 parameters Vector of size get_num_parameters(), contains the parameters of the layer

Reimplemented in CNeuralLinearLayer, CNeuralLogisticLayer, and CNeuralRectifiedLinearLayer.

Definition at line 242 of file NeuralLayer.h.

## ◆ compute_error()

 virtual float64_t compute_error ( SGMatrix< float64_t > targets )
virtual

Computes the error between the layer's current activations and the given target activations. Should only be used with output layers

Parameters
 targets desired values for the layer's activations, matrix of size num_neurons*batch_size

Reimplemented in CNeuralConvolutionalLayer, CNeuralLinearLayer, and CNeuralSoftmaxLayer.

Definition at line 206 of file NeuralLayer.h.

 virtual void compute_gradients ( SGVector< float64_t > parameters, SGMatrix< float64_t > targets, CDynamicObjectArray * layers, SGVector< float64_t > parameter_gradients )
virtual

Computes the gradients that are relevent to this layer:

• The gradients of the error with respect to the layer's parameters -The gradients of the error with respect to the layer's inputs

Deriving classes should make sure to account for [dropout](http://arxiv.org/abs/1207.0580) [Hinton, 2012] during gradient computations

Deriving classes should also account for contraction_coefficient if they can be used in as a hidden layer in a contractive autoencoder.

Parameters
 parameters Vector of size get_num_parameters(), contains the parameters of the layer targets a matrix of size num_neurons*batch_size. If the layer is being used as an output layer, targets is the desired values for the layer's activations, otherwise it's an empty matrix layers Array of layers that form the network that this layer is being used with parameter_gradients Vector of size get_num_parameters(). To be filled with gradients of the error with respect to each parameter of the layer

Reimplemented in CNeuralConvolutionalLayer, and CNeuralLinearLayer.

Definition at line 195 of file NeuralLayer.h.

## ◆ deep_copy()

 CSGObject * deep_copy ( ) const
virtualinherited

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

Definition at line 232 of file SGObject.cpp.

## ◆ dropout_activations()

 void dropout_activations ( )
virtual

Applies [dropout](http://arxiv.org/abs/1207.0580) [Hinton, 2012] to the activations of the layer

If is_training is true, fills m_dropout_mask with random values (according to dropout_prop) and multiplies it into the activations, otherwise, multiplies the activations by (1-dropout_prop) to compensate for using dropout during training

Definition at line 90 of file NeuralLayer.cpp.

## ◆ enforce_max_norm()

 virtual void enforce_max_norm ( SGVector< float64_t > parameters, float64_t max_norm )
virtual

Constrains the weights of each neuron in the layer to have an L2 norm of at most max_norm

Parameters
 parameters pointer to the layer's parameters, array of size get_num_parameters() max_norm maximum allowable norm for a neuron's weights

Reimplemented in CNeuralConvolutionalLayer, and CNeuralLinearLayer.

Definition at line 216 of file NeuralLayer.h.

## ◆ equals()

 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 656 of file SGObject.cpp.

## ◆ get() [1/2]

 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 381 of file SGObject.h.

## ◆ get() [2/2]

 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 404 of file SGObject.h.

virtual

Gets the layer's activation gradients, a matrix of size num_neurons * batch_size

Returns

Definition at line 294 of file NeuralLayer.h.

## ◆ get_activations()

 virtual SGMatrix get_activations ( )
virtual

Gets the layer's activations, a matrix of size num_neurons * batch_size

Returns
layer's activations

Definition at line 287 of file NeuralLayer.h.

## ◆ get_global_io()

 SGIO * get_global_io ( )
inherited

get the io object

Returns
io object

Definition at line 269 of file SGObject.cpp.

## ◆ get_global_parallel()

 Parallel * get_global_parallel ( )
inherited

get the parallel object

Returns
parallel object

Definition at line 311 of file SGObject.cpp.

## ◆ get_global_version()

 Version * get_global_version ( )
inherited

get the version object

Returns
version object

Definition at line 324 of file SGObject.cpp.

## ◆ get_height()

 virtual int32_t get_height ( )
virtual

Returns the height assuming that the layer's activations are interpreted as images (i.e for convolutional nets)

Returns
Height

Definition at line 265 of file NeuralLayer.h.

## ◆ get_input_indices()

 virtual SGVector get_input_indices ( )
virtual

Gets the indices of the layers that are connected to this layer as input

Returns
layer's input indices

Definition at line 313 of file NeuralLayer.h.

virtual

Gets the layer's local gradients, a matrix of size num_neurons * batch_size

Returns

Definition at line 304 of file NeuralLayer.h.

## ◆ get_modelsel_names()

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

Definition at line 536 of file SGObject.cpp.

## ◆ get_modsel_param_descr()

 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 560 of file SGObject.cpp.

## ◆ get_modsel_param_index()

 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 573 of file SGObject.cpp.

## ◆ get_name()

 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 315 of file NeuralLayer.h.

## ◆ get_num_neurons()

 virtual int32_t get_num_neurons ( )
virtual

Gets the number of neurons in the layer

Returns
number of neurons in the layer

Definition at line 251 of file NeuralLayer.h.

## ◆ get_num_parameters()

 virtual int32_t get_num_parameters ( )
virtual

Gets the number of parameters used in this layer

Returns
number of parameters used in this layer

Definition at line 281 of file NeuralLayer.h.

## ◆ get_parameters_observable()

 SGObservable* get_parameters_observable ( )
inherited

Get parameters observable

Returns
RxCpp observable

Definition at line 415 of file SGObject.h.

## ◆ get_width()

 virtual int32_t get_width ( )
virtual

Returns the width assuming that the layer's activations are interpreted as images (i.e for convolutional nets)

Returns
Width

Definition at line 258 of file NeuralLayer.h.

## ◆ has() [1/3]

 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 304 of file SGObject.h.

## ◆ has() [2/3]

 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 315 of file SGObject.h.

## ◆ has() [3/3]

 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 326 of file SGObject.h.

## ◆ initialize_neural_layer()

 void initialize_neural_layer ( CDynamicObjectArray * layers, SGVector< int32_t > input_indices )
virtual

Initializes the layer

Parameters
 layers Array of layers that form the network that this layer is being used with input_indices Indices of the layers that are connected to this layer as input

Reimplemented in CNeuralConvolutionalLayer, and CNeuralLinearLayer.

Definition at line 61 of file NeuralLayer.cpp.

## ◆ initialize_parameters()

 virtual void initialize_parameters ( SGVector< float64_t > parameters, SGVector< bool > parameter_regularizable, float64_t sigma )
virtual

Initializes the layer's parameters. The layer should fill the given arrays with the initial value for its parameters

Parameters
 parameters Vector of size get_num_parameters() parameter_regularizable Vector of size get_num_parameters(). This controls which of the layer's parameter are subject to regularization, i.e to turn off regularization for parameter i, set parameter_regularizable[i] = false. This is usally used to turn off regularization for bias parameters. sigma standard deviation of the gaussian used to random the parameters

Reimplemented in CNeuralConvolutionalLayer, and CNeuralLinearLayer.

Definition at line 143 of file NeuralLayer.h.

## ◆ is_generic()

 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 330 of file SGObject.cpp.

## ◆ is_input()

 virtual bool is_input ( )
virtual

returns true if the layer is an input layer. Input layers are the root layers of a network, that is, they don't receive signals from other layers, they receive signals from the inputs features to the network.

Local and activation gradients are not computed for input layers

Reimplemented in CNeuralInputLayer.

Definition at line 127 of file NeuralLayer.h.

## ◆ list_observable_parameters()

 void list_observable_parameters ( )
inherited

Print to stdout a list of observable parameters

Definition at line 878 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 403 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 460 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 455 of file SGObject.cpp.

## ◆ observe()

 void observe ( const ObservedValue value )
protectedinherited

Observe a parameter value and emit them to observer.

Parameters
 value Observed parameter's value

Definition at line 828 of file SGObject.cpp.

## ◆ parameter_hash_changed()

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

Definition at line 296 of file SGObject.cpp.

## ◆ print_modsel_params()

 void print_modsel_params ( )
inherited

prints all parameter registered for model selection and their type

Definition at line 512 of file SGObject.cpp.

## ◆ print_serializable()

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

prints registered parameters out

Parameters
 prefix prefix for members

Definition at line 342 of file SGObject.cpp.

## ◆ ref()

 int32_t ref ( )
inherited

increase reference counter

Returns
reference count

Definition at line 186 of file SGObject.cpp.

## ◆ ref_count()

 int32_t ref_count ( )
inherited

display reference counter

Returns
reference count

Definition at line 193 of file SGObject.cpp.

## ◆ register_observable_param()

 void register_observable_param ( const std::string & name, const SG_OBS_VALUE_TYPE type, const std::string & description )
protectedinherited

Register which params this object can emit.

Parameters
 name the param name type the param type description a user oriented description

Definition at line 871 of file SGObject.cpp.

## ◆ register_param() [1/2]

 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 472 of file SGObject.h.

## ◆ register_param() [2/2]

 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 485 of file SGObject.h.

## ◆ save_serializable()

 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 348 of file SGObject.cpp.

## ◆ save_serializable_post()

 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 470 of file SGObject.cpp.

## ◆ save_serializable_pre()

 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 465 of file SGObject.cpp.

## ◆ set() [1/2]

 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 342 of file SGObject.h.

## ◆ set() [2/2]

 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 368 of file SGObject.h.

## ◆ set_batch_size()

 void set_batch_size ( int32_t batch_size )
virtual

Sets the batch_size and allocates memory for m_activations and m_input_gradients accordingly. Must be called before forward or backward propagation is performed

Parameters
 batch_size number of training/test cases the network is currently working with

Reimplemented in CNeuralConvolutionalLayer.

Definition at line 75 of file NeuralLayer.cpp.

## ◆ set_generic() [1/16]

 void set_generic ( )
inherited

Definition at line 73 of file SGObject.cpp.

## ◆ set_generic() [2/16]

 void set_generic ( )
inherited

Definition at line 78 of file SGObject.cpp.

## ◆ set_generic() [3/16]

 void set_generic ( )
inherited

Definition at line 83 of file SGObject.cpp.

## ◆ set_generic() [4/16]

 void set_generic ( )
inherited

Definition at line 88 of file SGObject.cpp.

## ◆ set_generic() [5/16]

 void set_generic ( )
inherited

Definition at line 93 of file SGObject.cpp.

## ◆ set_generic() [6/16]

 void set_generic ( )
inherited

Definition at line 98 of file SGObject.cpp.

## ◆ set_generic() [7/16]

 void set_generic ( )
inherited

Definition at line 103 of file SGObject.cpp.

## ◆ set_generic() [8/16]

 void set_generic ( )
inherited

Definition at line 108 of file SGObject.cpp.

## ◆ set_generic() [9/16]

 void set_generic ( )
inherited

Definition at line 113 of file SGObject.cpp.

## ◆ set_generic() [10/16]

 void set_generic ( )
inherited

Definition at line 118 of file SGObject.cpp.

## ◆ set_generic() [11/16]

 void set_generic ( )
inherited

Definition at line 123 of file SGObject.cpp.

## ◆ set_generic() [12/16]

 void set_generic ( )
inherited

Definition at line 128 of file SGObject.cpp.

## ◆ set_generic() [13/16]

 void set_generic ( )
inherited

Definition at line 133 of file SGObject.cpp.

## ◆ set_generic() [14/16]

 void set_generic ( )
inherited

Definition at line 138 of file SGObject.cpp.

## ◆ set_generic() [15/16]

 void set_generic ( )
inherited

Definition at line 143 of file SGObject.cpp.

## ◆ set_generic() [16/16]

 void set_generic ( )
inherited

set generic type to T

## ◆ set_global_io()

 void set_global_io ( SGIO * io )
inherited

set the io object

Parameters
 io io object to use

Definition at line 262 of file SGObject.cpp.

## ◆ set_global_parallel()

 void set_global_parallel ( Parallel * parallel )
inherited

set the parallel object

Parameters
 parallel parallel object to use

Definition at line 275 of file SGObject.cpp.

## ◆ set_global_version()

 void set_global_version ( Version * version )
inherited

set the version object

Parameters
 version version object to use

Definition at line 317 of file SGObject.cpp.

## ◆ set_num_neurons()

 virtual void set_num_neurons ( int32_t num_neurons )
virtual

Gets the number of neurons in the layer

Parameters
 num_neurons number of neurons in the layer

Definition at line 271 of file NeuralLayer.h.

## ◆ shallow_copy()

 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 226 of file SGObject.cpp.

## ◆ subscribe_to_parameters()

 void subscribe_to_parameters ( ParameterObserverInterface * obs )
inherited

Subscribe a parameter observer to watch over params

Definition at line 811 of file SGObject.cpp.

## ◆ unref()

 int32_t unref ( )
inherited

decrement reference counter and deallocate object if refcount is zero before or after decrementing it

Returns
reference count

Definition at line 200 of file SGObject.cpp.

## ◆ unset_generic()

 void unset_generic ( )
inherited

unset generic type

this has to be called in classes specializing a template class

Definition at line 337 of file SGObject.cpp.

## ◆ update_parameter_hash()

 void update_parameter_hash ( )
virtualinherited

Updates the hash of current parameter combination

Definition at line 282 of file SGObject.cpp.

## ◆ autoencoder_position

 ENLAutoencoderPosition autoencoder_position

For autoencoders, specifies the position of the layer in the autoencoder, i.e an encoding layer or a decoding layer. Default value is NLAP_NONE

Definition at line 343 of file NeuralLayer.h.

## ◆ contraction_coefficient

 float64_t contraction_coefficient

For hidden layers in a contractive autoencoders [Rifai, 2011] a term:

$\frac{\lambda}{N} \sum_{k=0}^{N-1} \left \| J(x_k) \right \|^2_F$

is added to the error, where $$\left \| J(x_k)) \right \|^2_F$$ is the Frobenius norm of the Jacobian of the activations of the hidden layer with respect to its inputs, $$N$$ is the batch size, and $$\lambda$$ is the contraction coefficient.

Default value is 0.0.

Definition at line 338 of file NeuralLayer.h.

## ◆ dropout_prop

 float64_t dropout_prop

probabilty of dropping out a neuron in the layer

Definition at line 327 of file NeuralLayer.h.

## ◆ io

 SGIO* io
inherited

io

Definition at line 600 of file SGObject.h.

## ◆ is_training

 bool is_training

Should be true if the layer is currently used during training initial value is false

Definition at line 324 of file NeuralLayer.h.

protected

gradients of the error with respect to the layer's inputs size previous_layer_num_neurons * batch_size

Definition at line 381 of file NeuralLayer.h.

## ◆ m_activations

 SGMatrix m_activations
protected

activations of the neurons in this layer size num_neurons * batch_size

Definition at line 376 of file NeuralLayer.h.

## ◆ m_batch_size

 int32_t m_batch_size
protected

number of training/test cases the network is currently working with

Definition at line 371 of file NeuralLayer.h.

protected

binary mask that determines whether a neuron will be kept or dropped out during the current iteration of training size num_neurons * batch_size

Definition at line 393 of file NeuralLayer.h.

inherited

parameters wrt which we can compute gradients

Definition at line 615 of file SGObject.h.

## ◆ m_hash

 uint32_t m_hash
inherited

Hash of parameter values

Definition at line 618 of file SGObject.h.

## ◆ m_height

 int32_t m_height
protected

Width of the image (if the layer's activations are to be interpreted as images. Default value is 1

Definition at line 357 of file NeuralLayer.h.

## ◆ m_input_indices

 SGVector m_input_indices
protected

Indices of the layers that are connected to this layer as input

Definition at line 363 of file NeuralLayer.h.

## ◆ m_input_sizes

 SGVector m_input_sizes
protected

Number of neurons in the layers that are connected to this layer as input

Definition at line 368 of file NeuralLayer.h.

protected

gradients of the error with respect to the layer's pre-activations, this is usually used as a buffer when computing the input gradients size num_neurons * batch_size

Definition at line 387 of file NeuralLayer.h.

## ◆ m_model_selection_parameters

 Parameter* m_model_selection_parameters
inherited

model selection parameters

Definition at line 612 of file SGObject.h.

## ◆ m_num_neurons

 int32_t m_num_neurons
protected

Number of neurons in this layer

Definition at line 347 of file NeuralLayer.h.

## ◆ m_num_parameters

 int32_t m_num_parameters
protected

Number of neurons in this layer

Definition at line 360 of file NeuralLayer.h.

## ◆ m_parameters

 Parameter* m_parameters
inherited

parameters

Definition at line 609 of file SGObject.h.

## ◆ m_width

 int32_t m_width
protected

Width of the image (if the layer's activations are to be interpreted as images. Default value is m_num_neurons

Definition at line 352 of file NeuralLayer.h.

## ◆ parallel

 Parallel* parallel
inherited

parallel

Definition at line 603 of file SGObject.h.

## ◆ version

 Version* version
inherited

version

Definition at line 606 of file SGObject.h.

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

SHOGUN Machine Learning Toolbox - Documentation