netkit.classifiers.active
Class EmpiricalRiskMinimization

java.lang.Object
  netkit.classifiers.active.PickLabelStrategyImp
      netkit.classifiers.active.EmpiricalRiskMinimization

All Implemented Interfaces:

PickLabelStrategy, Configurable

public class EmpiricalRiskMinimization
extends PickLabelStrategyImp

Nested Class Summary

Nested classes/interfaces inherited from interface netkit.classifiers.active.PickLabelStrategy

PickLabelStrategy.LabelNode

Field Summary

Fields inherited from class netkit.classifiers.active.PickLabelStrategyImp

iteration, logger

Constructor Summary

EmpiricalRiskMinimization()

Method Summary

static double	computeEmpiricalRisk(Estimate predictions) Compute the empirical risk for a specific set of predictions using the standard empirical risk formulation: risk(predictions) = sum over x in testset: argmin_i [ 1-f(x,i) ], where f(x,i) is the probability that x belongs to class i.
void	configure(Configuration config)
Configuration	getDefaultConfiguration()
java.lang.String	getDescription()
java.lang.String	getName()
java.lang.String	getShortName()
protected PickLabelStrategy.LabelNode[]	pickNodes(Estimate predictions, int maxPicks) Get the next nodes to label based on the empirical risk minimization principle.

Methods inherited from class netkit.classifiers.active.PickLabelStrategyImp

getAverageRank, getAverageRank, getIterationNum, getNetworkLearner, getNodesToLabel, getRank, getSplit, initialize, peek, toString

Methods inherited from class java.lang.Object

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

Constructor Detail

EmpiricalRiskMinimization

public EmpiricalRiskMinimization()

Method Detail

getDefaultConfiguration

public Configuration getDefaultConfiguration()

Specified by:

getDefaultConfiguration in interface Configurable

Overrides:

getDefaultConfiguration in class PickLabelStrategyImp

configure

public void configure(Configuration config)

Specified by:

configure in interface Configurable

Overrides:

configure in class PickLabelStrategyImp

computeEmpiricalRisk

public static double computeEmpiricalRisk(Estimate predictions)

Compute the empirical risk for a specific set of predictions using the standard empirical risk formulation:

risk(predictions) = sum over x in testset: argmin_i [ 1-f(x,i) ],

where f(x,i) is the probability that x belongs to class i.

Parameters:

predictions -

Returns:

the risk of these computations

pickNodes

protected PickLabelStrategy.LabelNode[] pickNodes(Estimate predictions,
                                                  int maxPicks)

Get the next nodes to label based on the empirical risk minimization principle.

Specified by:

pickNodes in class PickLabelStrategyImp

maxPicks - how many nodes should it pick at maximum (this iteration)

Returns:

An array of Node objects that should receive labels. null is returned if done.

getDescription

public java.lang.String getDescription()

getName

public java.lang.String getName()

getShortName

public java.lang.String getShortName()