mic::mlnn::HebbianNeuralNetwork< eT > Class Template Reference

Class representing a multi-layer neural network based on hebbian learning. More...

#include <HebbianNeuralNetwork.hpp>

Inheritance diagram for mic::mlnn::HebbianNeuralNetwork< eT >:

Collaboration diagram for mic::mlnn::HebbianNeuralNetwork< eT >:

Public Member Functions
	HebbianNeuralNetwork (std::string name_="hebbian_net")
virtual	~HebbianNeuralNetwork ()
	Virtual descriptor - empty. More...
void	forward (mic::types::MatrixPtr< eT > input_data, bool skip_dropout=false)
eT	train (mic::types::MatrixPtr< eT > encoded_batch_, eT learning_rate_)
eT	test (mic::types::MatrixPtr< eT > encoded_batch_)
Public Member Functions inherited from mic::mlnn::MultiLayerNeuralNetwork< eT >
	MultiLayerNeuralNetwork (std::string name_="mlnn")
virtual	~MultiLayerNeuralNetwork ()
template<typename LayerType >
void	pushLayer (LayerType *layer_ptr_)
template<typename LayerType >
std::shared_ptr< LayerType >	getLayer (size_t index_)
std::shared_ptr< Layer< eT > >	getLayer (size_t index_)
void	popLayer (size_t number_of_layers_=1)
size_t	layerInputsSize (size_t layer_number_=-1)
size_t	lastLayerOutputsSize (size_t layer_number_=-1)
size_t	lastLayerBatchSize (size_t layer_number_=-1)
template<typename omT >
void	setOptimization ()
void	update (eT alpha_, eT decay_=0.0f)
void	resetGrads ()
void	resizeBatch (size_t batch_size_)
mic::types::MatrixPtr< eT >	getPredictions ()
mic::types::MatrixPtr< eT >	getPredictions (size_t layer_nr_)
size_t	countCorrectPredictions (mic::types::MatrixPtr< eT > targets_, mic::types::MatrixPtr< eT > predictions_)
bool	save (std::string filename_)
bool	load (std::string filename_)

Additional Inherited Members
Protected Attributes inherited from mic::mlnn::MultiLayerNeuralNetwork< eT >
std::vector< std::shared_ptr < mic::mlnn::Layer< eT > > >	layers
std::string	name
bool	connected
	Flag denoting whether the layers are interconnected, thus no copying between inputs and outputs of the neighboring layers will be required. More...

Detailed Description

template<typename eT>
class mic::mlnn::HebbianNeuralNetwork< eT >

Class representing a multi-layer neural network based on hebbian learning.

Author

tkornuta

Template Parameters

eT	Template parameter denoting precision of variables (float for calculations/double for testing).

Definition at line 41 of file HebbianNeuralNetwork.hpp.

Constructor & Destructor Documentation

template<typename eT >

mic::mlnn::HebbianNeuralNetwork< eT >::HebbianNeuralNetwork ( std::string  name_ = "hebbian_net" )

inline

Constructor. Sets the neural network name.

Parameters

name_

Name of the network.

Definition at line 49 of file HebbianNeuralNetwork.hpp.

template<typename eT >

virtual mic::mlnn::HebbianNeuralNetwork< eT >::~HebbianNeuralNetwork ( )

inlinevirtual

Virtual descriptor - empty.

Definition at line 57 of file HebbianNeuralNetwork.hpp.

Member Function Documentation

template<typename eT >

void mic::mlnn::HebbianNeuralNetwork< eT >::forward ( mic::types::MatrixPtr< eT >  input_data, bool  skip_dropout = false  )

inline

Passes the data in a feed-forward manner through all consecutive layers, from the input to the output layer.

Parameters

input_data	Input data - a matrix containing [sample_size x batch_size].
skip_dropout	Flag for skipping dropouts - which should be set to true during testing.

Definition at line 65 of file HebbianNeuralNetwork.hpp.

References mic::mlnn::MultiLayerNeuralNetwork< eT >::connected, mic::mlnn::MultiLayerNeuralNetwork< eT >::layers, and mic::mlnn::MultiLayerNeuralNetwork< eT >::resizeBatch().

Referenced by mic::mlnn::HebbianNeuralNetwork< eT >::test(), and mic::mlnn::HebbianNeuralNetwork< eT >::train().

Here is the call graph for this function:

template<typename eT >

eT mic::mlnn::HebbianNeuralNetwork< eT >::test ( mic::types::MatrixPtr< eT >  encoded_batch_ )

inline

Tests the neural network with a given batch.

Parameters

encoded_batch_	Batch encoded in the form of matrix of size [sample_size x batch_size].
encoded_targets_	Targets (labels) encoded in the form of matrix of size [label_size x batch_size].

Returns

Loss computed according to the selected loss function. If function not set - returns INF.

Definition at line 140 of file HebbianNeuralNetwork.hpp.

References mic::mlnn::HebbianNeuralNetwork< eT >::forward().

Here is the call graph for this function:

template<typename eT >

eT mic::mlnn::HebbianNeuralNetwork< eT >::train ( mic::types::MatrixPtr< eT >  encoded_batch_, eT  learning_rate_  )

inline

Trains the neural network with a given batch.

Parameters

encoded_batch_	Batch encoded in the form of matrix of size [sample_size x batch_size].
learning_rate_	The learning rate.

Returns

Loss computed according to the selected loss function. If function not set - returns INF.

Definition at line 118 of file HebbianNeuralNetwork.hpp.

References mic::mlnn::HebbianNeuralNetwork< eT >::forward(), and mic::mlnn::MultiLayerNeuralNetwork< eT >::update().

Here is the call graph for this function:

---

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

• src/mlnn/HebbianNeuralNetwork.hpp