yawn.nn.committee
Class NetworkCommittee

java.lang.Object
  extended by yawn.nn.NeuralNetwork
      extended by yawn.nn.committee.NetworkCommittee
All Implemented Interfaces:
java.io.Serializable

public class NetworkCommittee
extends NeuralNetwork

A committe or set of neural networks to be trained and used concurrently to provide a consistent learning experiment and predictions. $Id: NetworkCommittee.java,v 1.5 2005/04/07 17:28:07 supermarti Exp $

Version:
$Revision: 1.5 $
Author:
Luis Martí (luis dot marti at uc3m dot es)
See Also:
Serialized Form

Nested Class Summary
 class NetworkCommittee.TrainRunner
          Utility class for multi-threaded training of neural networks.
 
Field Summary
protected  CommitteeFunction combinationFunction
          the function used to combine the results from each committe member
protected  java.util.List committee
           
protected  boolean serialProcessing
           
 
Constructor Summary
NetworkCommittee()
           
NetworkCommittee(CommitteeFunction combinationFunction)
           
 
Method Summary
 void addCommitteeMembers(NeuralNetwork member)
           
 CommitteeFunction getCombinationFunction()
           
 java.util.List getCommitteMembers()
           
 int getCommitteSize()
           
 int getInputSize()
           
 java.lang.String getNeuralNetworkName()
          Returns a human readable
 int getOutputSize()
           
 boolean isSerialProcessing()
           
 void oneLearningStep(Pattern input, Pattern output)
          this has no sense in this context, throws an UnsupportedOperationException by default.
 Pattern predict(Pattern input)
          Computes a network prediction
 void setCombinationFunction(CommitteeFunction combinationFunction)
           
 void setSerialProcessing(boolean serialProcessing)
           
 void setup(NeuralNetworkConfig config)
           
 void train(InputOutputPattern[] iop)
          Trains the network until the stop criteria is met.
 NeuralNetworkConfig yieldConfiguration()
           
 
Methods inherited from class yawn.nn.NeuralNetwork
getAdapting, getStatisticsFacility, isAdapting, setAdapting, setStatisticsFacility
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

combinationFunction

protected CommitteeFunction combinationFunction
the function used to combine the results from each committe member


committee

protected java.util.List committee

serialProcessing

protected boolean serialProcessing
Constructor Detail

NetworkCommittee

public NetworkCommittee()

NetworkCommittee

public NetworkCommittee(CommitteeFunction combinationFunction)
Method Detail

addCommitteeMembers

public void addCommitteeMembers(NeuralNetwork member)

getCommitteMembers

public java.util.List getCommitteMembers()

oneLearningStep

public void oneLearningStep(Pattern input,
                            Pattern output)
this has no sense in this context, throws an UnsupportedOperationException by default.

Specified by:
oneLearningStep in class NeuralNetwork
Parameters:
input - The network input.
output - The desired output.

predict

public Pattern predict(Pattern input)
Description copied from class: NeuralNetwork
Computes a network prediction

Specified by:
predict in class NeuralNetwork
Parameters:
input - The input to propagate.
Returns:
the network output.
See Also:
NeuralNetwork.predict(yawn.util.Pattern)

train

public void train(InputOutputPattern[] iop)
Description copied from class: NeuralNetwork
Trains the network until the stop criteria is met.

Specified by:
train in class NeuralNetwork
Parameters:
iop - The training set to be learned.
See Also:
NeuralNetwork.train(yawn.util.InputOutputPattern[])

getCombinationFunction

public CommitteeFunction getCombinationFunction()
Returns:
Returns the combinationFunction.

getCommitteSize

public int getCommitteSize()
Returns:
Returns the committeSize.

getNeuralNetworkName

public java.lang.String getNeuralNetworkName()
Description copied from class: NeuralNetwork
Returns a human readable

Specified by:
getNeuralNetworkName in class NeuralNetwork
Returns:
The name

setCombinationFunction

public void setCombinationFunction(CommitteeFunction combinationFunction)
Parameters:
combinationFunction - The combinationFunction to set.

getInputSize

public int getInputSize()
Specified by:
getInputSize in class NeuralNetwork

getOutputSize

public int getOutputSize()
Specified by:
getOutputSize in class NeuralNetwork

setup

public void setup(NeuralNetworkConfig config)
           throws ConfigurationException
Specified by:
setup in class NeuralNetwork
Throws:
ConfigurationException

yieldConfiguration

public NeuralNetworkConfig yieldConfiguration()
Specified by:
yieldConfiguration in class NeuralNetwork
See Also:
NeuralNetwork.yieldConfiguration()

isSerialProcessing

public boolean isSerialProcessing()
Returns:
Returns the serialProcessing.

setSerialProcessing

public void setSerialProcessing(boolean serialProcessing)
Parameters:
serialProcessing - The serialProcessing to set.


Copyright © 2003-2005 GIAA, Universidad Carlos III de Madrid. All Rights Reserved.