GPUMLib  0.2.2
GPU Machine Learning Library
Public Member Functions | List of all members
KMeans Class Reference

Represents a clustering algorithm using the K-Means technique, implemented in CUDA. More...

#include <KMeans.h>

Public Member Functions

 KMeans ()
 Base class for the KMeans algorithm.
 
DeviceMatrix< float > Execute_TI (DeviceMatrix< float > &Input, int kneighbours)
 
DeviceMatrix< float > Execute (DeviceMatrix< float > &Input, int kneighbours)
 
void SetSeed (unsigned int seed)
 
unsigned int GetSeed ()
 

Detailed Description

Represents a clustering algorithm using the K-Means technique, implemented in CUDA.

Definition at line 58 of file KMeans.h.

Member Function Documentation

DeviceMatrix< float > Execute ( DeviceMatrix< float > &  Input,
int  kneighbours 
)

Executes the standard K-Means algorithm.

Parameters
Inputmatrix to apply clustering.
kneighboursnumber of clusters desired.
Returns
Matrix with the selected cluster centroids.

Definition at line 155 of file KMeans.cpp.

DeviceMatrix< float > Execute_TI ( DeviceMatrix< float > &  Input,
int  kneighbours 
)

Executes a clustering algorithm, using the triangle inequality property.

Parameters
Inputmatrix to apply clustering.
kneighboursnumber of clusters desired.
Returns
Matrix with the selected cluster centroids.

Definition at line 64 of file KMeans.cpp.


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