shark::DistantModes Class Reference

Creates a set of pattern (each later representing a mode) which than are randomly perturbed to create the data set. The dataset was introduced in Desjardins et al. (2010) (Parallel Tempering for training restricted Boltzmann machines, AISTATS 2010) More...

#include <shark/Unsupervised/RBM/Problems/DistantModes.h>

Public Member Functions

 DistantModes (double p=0, unsigned dim=16, unsigned modes=4, unsigned copies=2500, size_t batchSize=0)
 
UnlabeledData< RealVector > data () const
 returns the generated dataset More...
 
std::size_t inputDimension () const
 returns the dimensionality of the data More...
 

Detailed Description

Creates a set of pattern (each later representing a mode) which than are randomly perturbed to create the data set. The dataset was introduced in Desjardins et al. (2010) (Parallel Tempering for training restricted Boltzmann machines, AISTATS 2010)

The higher the perturbation is the harder it is to classify, but the closer are the modes and thus the easier the data distribution is to learn.

Definition at line 45 of file DistantModes.h.

Constructor & Destructor Documentation

◆ DistantModes()

shark::DistantModes::DistantModes ( double  p = 0,
unsigned  dim = 16,
unsigned  modes = 4,
unsigned  copies = 2500,
size_t  batchSize = 0 
)
inline

generates the DistantModes distribution.

Parameters
pthe probability of changing a input neuron
dimthe dimensionality of the data.
modesthe number of modes, should be a multiple of 2
copiesthe number of disturbed copies for each mode
batchSizethe size of the batches in which the generated data set is organized

Definition at line 93 of file DistantModes.h.

Member Function Documentation

◆ data()

UnlabeledData<RealVector> shark::DistantModes::data ( ) const
inline

returns the generated dataset

Definition at line 99 of file DistantModes.h.

◆ inputDimension()

std::size_t shark::DistantModes::inputDimension ( ) const
inline

returns the dimensionality of the data

Definition at line 104 of file DistantModes.h.


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