|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectorg.joone.engine.Synapse
org.joone.io.StreamInputSynapse
org.joone.io.InputSwitchSynapse
org.joone.util.LearningSwitch
public class LearningSwitch
This class is useful to switch the input data set of a neural network from a training set to a validation set depending on the 'validation' parameter contained in the Monitor object. Very useful during a training phase to test the generalization capacity of the neural network with a validation data set never seen before.
Field Summary |
---|
Fields inherited from class org.joone.io.InputSwitchSynapse |
---|
inputs |
Fields inherited from class org.joone.io.StreamInputSynapse |
---|
cols, currentRow, EOF, InputVector, tokens |
Fields inherited from class org.joone.engine.Synapse |
---|
array, b_pattern, bitems, bouts, count, enabled, fwdLock, inps, items, learnable, m_batch, m_pattern, myLearner, notFirstTime, notFirstTimeB, outs, revLock |
Constructor Summary | |
---|---|
LearningSwitch()
Creates a new instance of LearningSwitch |
Method Summary | |
---|---|
boolean |
addTrainingSet(StreamInputSynapse tSet)
|
boolean |
addValidationSet(StreamInputSynapse vSet)
|
java.util.TreeSet |
check()
Check that parameters are set correctly. |
Pattern |
fwdGet()
Connects the right input synapse depending on the Monitor's 'validation' parameter |
Pattern |
fwdGet(InputConnector conn)
Connects the right input synapse depending on the Monitor's 'validation' parameter. |
StreamInputSynapse |
getTrainingSet()
Getter for property trainingSet. |
StreamInputSynapse |
getValidationSet()
Getter for property validationSet. |
void |
removeTrainingSet()
|
void |
removeValidationSet()
|
void |
setTrainingSet(StreamInputSynapse trainingSet)
Setter for property trainingSet. |
void |
setValidationSet(StreamInputSynapse validationSet)
Setter for property validationSet. |
Methods inherited from class org.joone.engine.Synapse |
---|
addNoise, canCountSteps, fwdPut, getFwdLock, getIgnoreBefore, getInputDimension, getLearner, getLearningRate, getMomentum, getRevLock, getWeights, initLearner, isEnabled, isInputFull, isLoopBack, isOutputFull, randomize, readResolve, revGet, setEnabled, setIgnoreBefore, setInputDimension, setInputFull, setLearningRate, setLoopBack, setMomentum, setOutputFull, setWeights |
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Constructor Detail |
---|
public LearningSwitch()
Method Detail |
---|
public boolean addTrainingSet(StreamInputSynapse tSet)
public boolean addValidationSet(StreamInputSynapse vSet)
public void removeTrainingSet()
public void removeValidationSet()
public Pattern fwdGet()
fwdGet
in interface InputPatternListener
fwdGet
in class InputSwitchSynapse
public Pattern fwdGet(InputConnector conn)
fwdGet
in class InputSwitchSynapse
public java.util.TreeSet check()
InputSwitchSynapse
check
in interface NeuralElement
check
in class InputSwitchSynapse
Synapse
public StreamInputSynapse getTrainingSet()
public void setTrainingSet(StreamInputSynapse trainingSet)
trainingSet
- New value of property trainingSet.public StreamInputSynapse getValidationSet()
public void setValidationSet(StreamInputSynapse validationSet)
validationSet
- New value of property validationSet.
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |