org.neuroph.eval

Class ClassifierEvaluator.MultiClass

java.lang.Object

org.neuroph.eval.ClassifierEvaluator

org.neuroph.eval.ClassifierEvaluator.MultiClass

All Implemented Interfaces:

Evaluator<ConfusionMatrix>

Enclosing class:

ClassifierEvaluator

public static class ClassifierEvaluator.MultiClass
extends ClassifierEvaluator

Evaluator used for computation of metrics in case when data has multiple classes - one vs many classification

Nested Class Summary

Nested classes/interfaces inherited from class org.neuroph.eval.ClassifierEvaluator

ClassifierEvaluator.Binary, ClassifierEvaluator.MultiClass

Constructor Summary

Constructors

Constructor and Description
MultiClass(String[] classLabels)

Method Summary

Modifier and Type	Method and Description
void	processNetworkResult(double[] predictedOutput, double[] actualOutput) This method should handle processing of a single network output within an evaluation procedure

Methods inherited from class org.neuroph.eval.ClassifierEvaluator

getResult, getThreshold, reset, setThreshold

Methods inherited from class java.lang.Object

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

Constructor Detail

MultiClass

public MultiClass(String[] classLabels)

Method Detail

processNetworkResult

public void processNetworkResult(double[] predictedOutput,
                                 double[] actualOutput)

Description copied from interface: Evaluator

This method should handle processing of a single network output within an evaluation procedure

Parameters:

predictedOutput - actual network output

actualOutput - desired/target network output