Direct Graphical Models  v.1.7.0
Graph Building

Sub-module containing methods for building arbitrary pairwise and dense graphical models. More...

Collaboration diagram for Graph Building:

Modules

 Graph Extensions
 A set of wrappers for building graphical models for 2D image classifaction.
 
 Graph Kit
 Kit (factory) for constructing Graph-related objects.
 

Classes

class  DirectGraphicalModels::CEdgeModelPotts
 Potts Edge Model for dense graphical models. More...
 
class  DirectGraphicalModels::CGraph
 Interface class for graphical models. More...
 
class  DirectGraphicalModels::CGraph3
 Triple graph class. More...
 
class  DirectGraphicalModels::CGraphDense
 Fully-connected (dense) graph class. More...
 
class  DirectGraphicalModels::CGraphPairwise
 Pairwise graph class. More...
 
class  DirectGraphicalModels::CGraphWeiss
 Pairwise graph class. More...
 
class  DirectGraphicalModels::IEdgeModel
 Interface class for edge models used in dense graphical models. More...
 
class  DirectGraphicalModels::IGraphPairwise
 Interface class for graphical models. More...
 

Detailed Description

Sub-module containing methods for building arbitrary pairwise and dense graphical models.

The underlying probability distributions of probabilistic models for sake of simplicity and flexibility of modeling are usually represented in a graphical form (this is why they are often called probabilistic graphical models). A probabilistic graphical model is a diagrammatic representation of a probability distribution. In such a graph there is a node for each random variable and relations between these variables are represented via graph edges.