Module es.upm.fi.cig.multictbnc

Package es.upm.fi.cig.multictbnc.learning.structure.optimisation.hillclimbing

Class RandomRestartHillClimbing

java.lang.Object

es.upm.fi.cig.multictbnc.learning.structure.optimisation.hillclimbing.HillClimbing

es.upm.fi.cig.multictbnc.learning.structure.optimisation.hillclimbing.RandomRestartHillClimbing

All Implemented Interfaces:

StructureLearningAlgorithm

public class RandomRestartHillClimbing
extends HillClimbing

Implements random-restart hill climbing.

Constructor Summary

Constructors

Constructor	Description
RandomRestartHillClimbing(HillClimbingImplementation hcImplementation, int numRestarts)	Constructs a RandomRestartHillClimbing by receiving the implementation of the hill climbing algorithm (for a Bayesian network, continuous-time Bayesian network...) and the number of restarts.

Method Summary

Modifier and Type	Method	Description
boolean[][]	findStructure()	Performs greedy Hill climbing to find a better structure than the initial one.
boolean[][]	findStructure(int idxNode)	Performs greedy Hill climbing to find a better local structure for a given node.
boolean[][]	findStructure(List<Integer> idxNodes)	Performs greedy Hill climbing to find a better local structure for some given nodes.
String	getIdentifier()	Returns a unique identifier for the structure learning algorithm.
Map<String,String>	getParametersAlgorithm()	Returns the parameters that are used by the algorithm.

Methods inherited from class es.upm.fi.cig.multictbnc.learning.structure.optimisation.hillclimbing.HillClimbing

learn, learn, learn

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

RandomRestartHillClimbing

public RandomRestartHillClimbing(HillClimbingImplementation hcImplementation,
 int numRestarts)

Constructs a RandomRestartHillClimbing by receiving the implementation of the hill climbing algorithm (for a Bayesian network, continuous-time Bayesian network...) and the number of restarts.

Parameters:

hcImplementation - implementation of the hill climbing algorithm

numRestarts - number of restarts

Method Details

findStructure

public boolean[][] findStructure()

Description copied from class: HillClimbing

Performs greedy Hill climbing to find a better structure than the initial one.

Specified by:

findStructure in class HillClimbing

Returns:

found adjacency matrix

findStructure

public boolean[][] findStructure(int idxNode)

Description copied from class: HillClimbing

Performs greedy Hill climbing to find a better local structure for a given node.

Specified by:

findStructure in class HillClimbing

Parameters:

idxNode - node index

Returns:

adjacency matrix found

findStructure

public boolean[][] findStructure(List<Integer> idxNodes)

Description copied from class: HillClimbing

Performs greedy Hill climbing to find a better local structure for some given nodes.

Specified by:

findStructure in class HillClimbing

Parameters:

idxNodes - node indexes

Returns:

adjacency matrix found

getIdentifier

public String getIdentifier()

Description copied from interface: StructureLearningAlgorithm

Returns a unique identifier for the structure learning algorithm.

Specified by:

getIdentifier in interface StructureLearningAlgorithm

Overrides:

getIdentifier in class HillClimbing

Returns:

unique identifier for the structure learning algorithm

getParametersAlgorithm

public Map<String,String> getParametersAlgorithm()

Description copied from interface: StructureLearningAlgorithm

Returns the parameters that are used by the algorithm.

Specified by:

getParametersAlgorithm in interface StructureLearningAlgorithm

Overrides:

getParametersAlgorithm in class HillClimbing

Returns:

a Map with the parameters used by the algorithm