Package dk.alexandra.fresco.stat.mlp.evaluation

Class Accuracy

Object

Accuracy

All Implemented Interfaces:

Computation<SInt,ProtocolBuilderNumeric>

public class Accuracy
extends Object
implements Computation<SInt,ProtocolBuilderNumeric>

Return the number of correct predictions in the given data set. The output of the given neural network is computed as the entry in the output vector with the highest value.

Constructor Summary

Constructors

Constructor	Description
Accuracy(MLP neuralNetwork, List<ArrayList<DRes<SFixed>>> data, ArrayList<DRes<SInt>> labels)

Method Summary

Modifier and Type	Method	Description
DRes<SInt>	buildComputation(ProtocolBuilderNumeric builder)

Methods inherited from class Object

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

Constructor Details

Accuracy

public Accuracy(MLP neuralNetwork, List<ArrayList<DRes<SFixed>>> data, ArrayList<DRes<SInt>> labels)

Method Details

buildComputation

public DRes<SInt> buildComputation(ProtocolBuilderNumeric builder)

Specified by:

buildComputation in interface Computation<SInt,ProtocolBuilderNumeric>