jMEF.BregmanHardClustering Class Reference

List of all members.

Static Public Member Functions
static MixtureModel	simplify (MixtureModel f, int m, Clustering.CLUSTERING_TYPE type, int iterations)
	Simplifies a mixture model f into a mixture model g of m components using Bregman hard clustering algorithm.
static MixtureModel	simplify (MixtureModel f, int m, Clustering.CLUSTERING_TYPE type)
	Simplifies a mixture model f into a mixture model g of m components using Bregman hard clustering algorithm.
static MixtureModel	simplify (MixtureModel f, MixtureModel g, Clustering.CLUSTERING_TYPE type)
	Simplifies a mixture model f into a mixture model g of m components using Bregman hard clustering algorithm.

---

Detailed Description

Author:

Vincent Garcia

Frank Nielsen

Version:

1.0

License

See file LICENSE.txt

Description

The Bregman hard clustering is the generalization of the hard clustering (also know as k-means) towards the exponential family. Given a set of weighted distributions (mixture model), the Bregman hard clustering partition the set into a determined number of classes. The centroid of each class is a weighted distribution. As a consequence, this algorithm simplifies a mixture model.

---

Member Function Documentation

static MixtureModel jMEF.BregmanHardClustering.simplify	(	MixtureModel	f,
		MixtureModel	g,
		Clustering.CLUSTERING_TYPE	type
	)			[static]

Simplifies a mixture model f into a mixture model g of m components using Bregman hard clustering algorithm.

Parameters:

	f	initial mixture model
	g	initialization of the mixture model g
	type	type of the Bregman divergence used (right-sided, left-sided, or symmetric)

Returns:

simplified mixture model g of m components

static MixtureModel jMEF.BregmanHardClustering.simplify	(	MixtureModel	f,
		int	m,
		Clustering.CLUSTERING_TYPE	type
	)			[static]

Simplifies a mixture model f into a mixture model g of m components using Bregman hard clustering algorithm.

Parameters:

	f	initial mixture model
	m	number of components in g
	type	type of the Bregman divergence used (right-sided, left-sided, or symmetric)

Returns:

simplified mixture model g of m components

static MixtureModel jMEF.BregmanHardClustering.simplify	(	MixtureModel	f,
		int	m,
		Clustering.CLUSTERING_TYPE	type,
		int	iterations
	)			[static]

Simplifies a mixture model f into a mixture model g of m components using Bregman hard clustering algorithm.

Parameters:

	f	initial mixture model
	m	number of components in g
	type	type of the Bregman divergence used (right-sided, left-sided, or symmetric)
	iterations	maximum number of iterations allowed

Returns:

simplified mixture model g of m components

---

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

• BregmanHardClustering.java