Package | Description |
---|---|
org.joone.engine | |
org.joone.engine.learning | |
org.joone.io | |
org.joone.net | |
org.joone.structure | |
org.joone.util |
Modifier and Type | Field and Description |
---|---|
protected Pattern |
Synapse.b_pattern |
protected Pattern |
Synapse.m_pattern |
Modifier and Type | Method and Description |
---|---|
Pattern |
BufferedSynapse.fwdGet()
Return the first element of the FIFO structure, if exists.
|
Pattern |
Synapse.fwdGet() |
Pattern |
InputPatternListener.fwdGet()
Returns the pattern coming from the previous layer during the recall phase
|
protected Pattern |
Synapse.fwdPattern_produce() |
static Pattern |
Pattern.makeStopPattern(int dim) |
static Pattern |
Pattern.makeZeroPattern(int dim) |
Pattern |
BufferedSynapse.revGet()
Not used
|
Pattern |
DirectSynapse.revGet() |
Pattern |
OutputSwitchSynapse.revGet()
Returns the error pattern coming from the next layer during the training phase
|
Pattern |
Synapse.revGet() |
Pattern |
OutputPatternListener.revGet()
Returns the error pattern coming from the next layer during the training phase
|
protected Pattern |
Synapse.revPattern_consume() |
Modifier and Type | Method and Description |
---|---|
protected void |
Layer.fireFwdPut(Pattern pattern)
Calls all the fwdPut methods on the output synapses to pass them the
calculated patterns
|
protected void |
Layer.fireRevPut(Pattern pattern)
Calls all the revPut methods on the input synapses to get the input
patterns and pass them the resulting calculated gradients
|
protected void |
Synapse.fwdPattern_consume(Pattern pattern) |
void |
BufferedSynapse.fwdPut(Pattern pattern)
Writes the input pattern into the FIFO structure.
|
void |
OutputSwitchSynapse.fwdPut(Pattern pattern)
Method to put a pattern forward to the next layer
|
void |
Synapse.fwdPut(Pattern pattern) |
void |
OutputPatternListener.fwdPut(Pattern pattern)
Method to put a pattern forward to the next layer
|
void |
Layer.fwdRun(Pattern pattIn)
Implementation code for the single-thread version of Joone.
|
protected void |
Synapse.revPattern_produce(Pattern pattern) |
void |
BufferedSynapse.revPut(Pattern pattern)
Not used
|
void |
DirectSynapse.revPut(Pattern pattern) |
void |
Synapse.revPut(Pattern pattern) |
void |
InputPatternListener.revPut(Pattern pattern)
Method to put an error pattern backward to the previous layer
|
void |
Layer.revRun(Pattern pattIn)
This method serves to a single backward step
when the Layer is called from an external thread
|
Modifier and Type | Method and Description |
---|---|
Pattern |
ComparisonSynapse.fwdGet() |
Pattern |
AbstractTeacherSynapse.fwdGet()
Here, it forwards (returns) the pushed error (in FIFO order).
|
Pattern |
TeachingSynapse.revGet() |
Pattern |
ComparisonSynapse.revGet()
Not used.
|
Pattern |
AbstractTeacherSynapse.revGet() |
Pattern |
ComparingSynapse.revGet() |
Modifier and Type | Method and Description |
---|---|
void |
TeacherSynapse.fwdPut(Pattern pattern) |
void |
TeachingSynapse.fwdPut(Pattern pattern) |
void |
ComparisonSynapse.fwdPut(Pattern pattern) |
void |
AbstractTeacherSynapse.fwdPut(Pattern pattern) |
void |
ComparingSynapse.fwdPut(Pattern pattern) |
void |
ComparisonSynapse.revPut(Pattern pattern)
Not used.
|
void |
AbstractTeacherSynapse.revPut(Pattern pattern) |
Modifier and Type | Method and Description |
---|---|
Pattern |
MultipleInputSynapse.fwdGet() |
Pattern |
InputSwitchSynapse.fwdGet()
Returns the pattern coming from the previous layer during the recall phase
|
Pattern |
StreamInputSynapse.fwdGet() |
Pattern |
MultipleInputSynapse.fwdGet(InputConnector conn) |
Pattern |
InputSwitchSynapse.fwdGet(InputConnector conn)
Returns the pattern coming from the previous layer during the recall phase.
|
Pattern |
StreamInputSynapse.fwdGet(InputConnector conn)
This method is called by the InputConnector in order
to get the next input pattern available for that connector
|
protected Pattern |
InputConnector.getStream() |
protected Pattern |
StreamInputSynapse.getStream() |
Pattern |
StreamOutputSynapse.revGet() |
protected Pattern |
StreamInputSynapse.zeroPattern() |
Modifier and Type | Method and Description |
---|---|
void |
StreamOutputSynapse.fwdPut(Pattern pattern)
The standard fwdPut method.
|
void |
InputSwitchSynapse.revPut(Pattern pattern)
Method to put an error pattern backward to the previous layer
|
void |
StreamInputSynapse.revPut(Pattern array) |
void |
ImageOutputSynapse.write(Pattern pattern)
Writes the Neural Network pattern to an Image file, the Image type is specified by
the ImageFileType property.
|
void |
MemoryOutputSynapse.write(Pattern pattern)
Custom Synapses need to implement at least this method.
|
void |
FileOutputSynapse.write(Pattern pattern)
Writes to the printer object.
|
abstract void |
StreamOutputSynapse.write(Pattern pattern)
Custom xxxOutputSynapses need to implement at least this method.
|
void |
JDBCOutputSynapse.write(Pattern pattern)
Writes the pattern data to the database specified in the dbURL.
|
void |
XLSOutputSynapse.write(Pattern pattern)
Writes a Pattern to the XLS file.
|
Modifier and Type | Method and Description |
---|---|
void |
NestedNeuralLayer.fwdRun(Pattern pattIn) |
void |
NestedNeuralLayer.revRun(Pattern pattIn) |
void |
NeuralNet.singleStepBackward(Pattern error)
Use this method to perform a single step backward.
|
void |
NeuralNet.singleStepForward(Pattern pattern)
Use this method to perform a single step forward.
|
protected void |
NeuralNet.stepBackward(Pattern error) |
protected void |
NeuralNet.stepForward(Pattern pattern) |
Modifier and Type | Method and Description |
---|---|
void |
PatternForwardedSynapse.fwdPut(Pattern pattern) |
Modifier and Type | Method and Description |
---|---|
Pattern |
LearningSwitch.fwdGet()
Connects the right input synapse depending on the
Monitor's 'validation' parameter
|
Pattern |
LearningSwitch.fwdGet(InputConnector conn)
Connects the right input synapse depending on the
Monitor's 'validation' parameter.
|
protected Pattern |
OutputConverterPlugIn.getPattern()
Gets the pattern that will be converted.
|
Modifier and Type | Method and Description |
---|---|
protected double |
RbfRandomCenterSelector.getDistance(Pattern aCenter1,
Pattern aCenter2)
Gets the distance between two centers.
|
void |
OutputConverterPlugIn.setPattern(Pattern newPattern)
Sets the current pattern to convert.
|
Submit Feedback to pmarrone@users.sourceforge.net