mlpack  2.0.1
Public Member Functions | Private Attributes | List of all members
mlpack::nn::SparseAutoencoder< OptimizerType > Class Template Reference

A sparse autoencoder is a neural network whose aim to learn compressed representations of the data, typically for dimensionality reduction, with a constraint on the activity of the neurons in the network. More...

Public Member Functions

 SparseAutoencoder (const arma::mat &data, const size_t visibleSize, const size_t hiddenSize, const double lambda=0.0001, const double beta=3, const double rho=0.01)
 Construct the sparse autoencoder model with the given training data. More...
 
 SparseAutoencoder (OptimizerType< SparseAutoencoderFunction > &optimizer)
 Construct the sparse autoencoder model with the given training data. More...
 
void Beta (const double b)
 Sets the KL divergence parameter. More...
 
double Beta () const
 Gets the KL divergence parameter. More...
 
void GetNewFeatures (arma::mat &data, arma::mat &features)
 Transforms the provided data into the representation learned by the sparse autoencoder. More...
 
void HiddenSize (const size_t hidden)
 Sets size of the hidden layer. More...
 
size_t HiddenSize () const
 Gets the size of the hidden layer. More...
 
void Lambda (const double l)
 Sets the L2-regularization parameter. More...
 
double Lambda () const
 Gets the L2-regularization parameter. More...
 
void Rho (const double r)
 Sets the sparsity parameter. More...
 
double Rho () const
 Gets the sparsity parameter. More...
 
void Sigmoid (const arma::mat &x, arma::mat &output) const
 Returns the elementwise sigmoid of the passed matrix, where the sigmoid function of a real number 'x' is [1 / (1 + exp(-x))]. More...
 
void VisibleSize (const size_t visible)
 Sets size of the visible layer. More...
 
size_t VisibleSize () const
 Gets size of the visible layer. More...
 

Private Attributes

double beta
 KL divergence parameter. More...
 
size_t hiddenSize
 Size of the hidden layer. More...
 
double lambda
 L2-regularization parameter. More...
 
arma::mat parameters
 Parameters after optimization. More...
 
double rho
 Sparsity parameter. More...
 
size_t visibleSize
 Size of the visible layer. More...
 

Detailed Description

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
class mlpack::nn::SparseAutoencoder< OptimizerType >

A sparse autoencoder is a neural network whose aim to learn compressed representations of the data, typically for dimensionality reduction, with a constraint on the activity of the neurons in the network.

Sparse autoencoders can be stacked together to learn a hierarchy of features, which provide a better representation of the data for classification. This is a method used in the recently developed field of deep learning. More technical details about the model can be found on the following webpage:

http://deeplearning.stanford.edu/wiki/index.php/UFLDL_Tutorial

An example of how to use the interface is shown below:

arma::mat data; // Data matrix.
const size_t vSize = 64; // Size of visible layer, depends on the data.
const size_t hSize = 25; // Size of hidden layer, depends on requirements.
// Train the model using default options.
SparseAutoencoder encoder1(data, vSize, hSize);
const size_t numBasis = 5; // Parameter required for L-BFGS algorithm.
const size_t numIterations = 100; // Maximum number of iterations.
// Use an instantiated optimizer for the training.
SparseAutoencoderFunction saf(data, vSize, hSize);
L_BFGS<SparseAutoencoderFunction> optimizer(saf, numBasis, numIterations);
SparseAutoencoder<L_BFGS> encoder2(optimizer);
arma::mat features1, features2; // Matrices for storing new representations.
// Get new representations from the trained models.
encoder1.GetNewFeatures(data, features1);
encoder2.GetNewFeatures(data, features2);

This implementation allows the use of arbitrary mlpack optimizers via the OptimizerType template parameter.

Template Parameters
OptimizerTypeThe optimizer to use; by default this is L-BFGS. Any mlpack optimizer can be used here.

Definition at line 70 of file sparse_autoencoder.hpp.

Constructor & Destructor Documentation

◆ SparseAutoencoder() [1/2]

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
mlpack::nn::SparseAutoencoder< OptimizerType >::SparseAutoencoder ( const arma::mat &  data,
const size_t  visibleSize,
const size_t  hiddenSize,
const double  lambda = 0.0001,
const double  beta = 3,
const double  rho = 0.01 
)

Construct the sparse autoencoder model with the given training data.

This will train the model. The parameters 'lambda', 'beta' and 'rho' can be set optionally. Changing these parameters will have an effect on regularization and sparsity of the model.

Parameters
dataInput data with each column as one example.
visibleSizeSize of input vector expected at the visible layer.
hiddenSizeSize of input vector expected at the hidden layer.
lambdaL2-regularization parameter.
betaKL divergence parameter.
rhoSparsity parameter.

◆ SparseAutoencoder() [2/2]

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
mlpack::nn::SparseAutoencoder< OptimizerType >::SparseAutoencoder ( OptimizerType< SparseAutoencoderFunction > &  optimizer)

Construct the sparse autoencoder model with the given training data.

This will train the model. This overload takes an already instantiated optimizer and uses it to train the model. The optimizer should hold an instantiated SparseAutoencoderFunction object for the function to operate upon. This option should be preferred when the optimizer options are to be changed.

Parameters
optimizerInstantiated optimizer with instantiated error function.

Member Function Documentation

◆ Beta() [1/2]

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
void mlpack::nn::SparseAutoencoder< OptimizerType >::Beta ( const double  b)
inline

Sets the KL divergence parameter.

Definition at line 162 of file sparse_autoencoder.hpp.

References mlpack::nn::SparseAutoencoder< OptimizerType >::beta.

◆ Beta() [2/2]

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
double mlpack::nn::SparseAutoencoder< OptimizerType >::Beta ( ) const
inline

Gets the KL divergence parameter.

Definition at line 168 of file sparse_autoencoder.hpp.

References mlpack::nn::SparseAutoencoder< OptimizerType >::beta.

◆ GetNewFeatures()

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
void mlpack::nn::SparseAutoencoder< OptimizerType >::GetNewFeatures ( arma::mat &  data,
arma::mat &  features 
)

Transforms the provided data into the representation learned by the sparse autoencoder.

The function basically performs a feedforward computation using the learned weights, and returns the hidden layer activations.

Parameters
dataMatrix of the provided data.
featuresThe hidden layer representation of the provided data.

◆ HiddenSize() [1/2]

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
void mlpack::nn::SparseAutoencoder< OptimizerType >::HiddenSize ( const size_t  hidden)
inline

Sets size of the hidden layer.

Definition at line 138 of file sparse_autoencoder.hpp.

◆ HiddenSize() [2/2]

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
size_t mlpack::nn::SparseAutoencoder< OptimizerType >::HiddenSize ( ) const
inline

Gets the size of the hidden layer.

Definition at line 144 of file sparse_autoencoder.hpp.

References mlpack::nn::SparseAutoencoder< OptimizerType >::hiddenSize.

◆ Lambda() [1/2]

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
void mlpack::nn::SparseAutoencoder< OptimizerType >::Lambda ( const double  l)
inline

Sets the L2-regularization parameter.

Definition at line 150 of file sparse_autoencoder.hpp.

References mlpack::nn::SparseAutoencoder< OptimizerType >::lambda.

◆ Lambda() [2/2]

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
double mlpack::nn::SparseAutoencoder< OptimizerType >::Lambda ( ) const
inline

Gets the L2-regularization parameter.

Definition at line 156 of file sparse_autoencoder.hpp.

References mlpack::nn::SparseAutoencoder< OptimizerType >::lambda.

◆ Rho() [1/2]

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
void mlpack::nn::SparseAutoencoder< OptimizerType >::Rho ( const double  r)
inline

Sets the sparsity parameter.

Definition at line 174 of file sparse_autoencoder.hpp.

References mlpack::nn::SparseAutoencoder< OptimizerType >::rho.

◆ Rho() [2/2]

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
double mlpack::nn::SparseAutoencoder< OptimizerType >::Rho ( ) const
inline

Gets the sparsity parameter.

Definition at line 180 of file sparse_autoencoder.hpp.

References mlpack::nn::SparseAutoencoder< OptimizerType >::rho.

◆ Sigmoid()

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
void mlpack::nn::SparseAutoencoder< OptimizerType >::Sigmoid ( const arma::mat &  x,
arma::mat &  output 
) const
inline

Returns the elementwise sigmoid of the passed matrix, where the sigmoid function of a real number 'x' is [1 / (1 + exp(-x))].

Parameters
xMatrix of real values for which we require the sigmoid activation.

Definition at line 120 of file sparse_autoencoder.hpp.

◆ VisibleSize() [1/2]

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
void mlpack::nn::SparseAutoencoder< OptimizerType >::VisibleSize ( const size_t  visible)
inline

Sets size of the visible layer.

Definition at line 126 of file sparse_autoencoder.hpp.

◆ VisibleSize() [2/2]

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
size_t mlpack::nn::SparseAutoencoder< OptimizerType >::VisibleSize ( ) const
inline

Gets size of the visible layer.

Definition at line 132 of file sparse_autoencoder.hpp.

References mlpack::nn::SparseAutoencoder< OptimizerType >::visibleSize.

Member Data Documentation

◆ beta

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
double mlpack::nn::SparseAutoencoder< OptimizerType >::beta
private

KL divergence parameter.

Definition at line 195 of file sparse_autoencoder.hpp.

Referenced by mlpack::nn::SparseAutoencoder< OptimizerType >::Beta().

◆ hiddenSize

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
size_t mlpack::nn::SparseAutoencoder< OptimizerType >::hiddenSize
private

Size of the hidden layer.

Definition at line 191 of file sparse_autoencoder.hpp.

Referenced by mlpack::nn::SparseAutoencoder< OptimizerType >::HiddenSize().

◆ lambda

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
double mlpack::nn::SparseAutoencoder< OptimizerType >::lambda
private

L2-regularization parameter.

Definition at line 193 of file sparse_autoencoder.hpp.

Referenced by mlpack::nn::SparseAutoencoder< OptimizerType >::Lambda().

◆ parameters

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
arma::mat mlpack::nn::SparseAutoencoder< OptimizerType >::parameters
private

Parameters after optimization.

Definition at line 187 of file sparse_autoencoder.hpp.

◆ rho

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
double mlpack::nn::SparseAutoencoder< OptimizerType >::rho
private

Sparsity parameter.

Definition at line 197 of file sparse_autoencoder.hpp.

Referenced by mlpack::nn::SparseAutoencoder< OptimizerType >::Rho().

◆ visibleSize

template<template< typename > class OptimizerType = mlpack::optimization::L_BFGS>
size_t mlpack::nn::SparseAutoencoder< OptimizerType >::visibleSize
private

Size of the visible layer.

Definition at line 189 of file sparse_autoencoder.hpp.

Referenced by mlpack::nn::SparseAutoencoder< OptimizerType >::VisibleSize().


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