org.joone.engine
Class DelayLayer

java.lang.Object
  org.joone.engine.Layer
      org.joone.engine.MemoryLayer
          org.joone.engine.DelayLayer

All Implemented Interfaces:

java.io.Serializable, java.lang.Runnable, Learnable, LearnableLayer, NeuralLayer, Inspectable

public class DelayLayer
extends MemoryLayer

Delay unit to create temporal windows from time series
O---> Yk(t-N)
|
...
|
O---> Yk(t-1)
|
O---> Yk(t)
|
|<--------- Xk(t)

Where:
Xk = Input signal
Yk(t)...Yk(t-N+1) = Values of the output temporal window
N = taps

See Also:

Serialized Form

Field Summary

Fields inherited from class org.joone.engine.MemoryLayer

backmemory, memory

Fields inherited from class org.joone.engine.Layer

bias, gradientInps, gradientOuts, inps, inputPatternListeners, learnable, learning, m_batch, monitor, myLearner, outputPatternListeners, outs, running, step, STOP_FLAG

Constructor Summary

DelayLayer()
Constructor method

DelayLayer(java.lang.String ElemName)
Constructor method

Method Summary

protected void	backward(double[] pattern) Reverse transfer function of the component.
java.util.TreeSet	check() Get check messages from listeners.
protected void	forward(double[] pattern) Transfer function to recall a result on a trained net
double	getDefaultState() Return the default state of a node in this layer, such as 0 for a tanh or 0.5 for a sigmoid layer
double	getDerivative(int i) Similar to the backward message and used by RTRL
double	getMaximumState() Return maximum value of a node in this layer
double	getMinimumState() Return minimum value of a node in this layer
java.util.Collection	Inspections() It doesn't make sense to return biases for this layer

Methods inherited from class org.joone.engine.MemoryLayer

getDimension, getTaps, setDimensions, setOutputDimension, setTaps, sumBackInput

Methods inherited from class org.joone.engine.Layer

addInputSynapse, addNoise, addOutputSynapse, adjustSizeToFwdPattern, adjustSizeToRevPattern, checkInputEnabled, checkInputs, checkOutputs, copyInto, finalize, fireFwdGet, fireFwdPut, fireRevGet, fireRevPut, fwdRun, getAllInputs, getAllOutputs, getBias, getLastGradientInps, getLastGradientOuts, getLastInputs, getLastOutputs, getLayerName, getLearner, getMonitor, getRows, getThreadMonitor, hasStepCounter, init, initLearner, InspectableTitle, isInputLayer, isOutputLayer, isRunning, join, randomize, randomizeBias, randomizeWeights, removeAllInputs, removeAllOutputs, removeInputSynapse, removeListener, removeOutputSynapse, resetInputListeners, revRun, run, setAllInputs, setAllOutputs, setBias, setConnDimensions, setInputDimension, setInputSynapses, setLastInputs, setLastOutputs, setLayerName, setMonitor, setOutputSynapses, setRows, start, stop, sumInput, toString

Methods inherited from class java.lang.Object

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

Constructor Detail

DelayLayer

public DelayLayer()

Constructor method

DelayLayer

public DelayLayer(java.lang.String ElemName)

Constructor method

Parameters:

ElemName - The layer's name

Method Detail

backward

protected void backward(double[] pattern)

Description copied from class: MemoryLayer

Reverse transfer function of the component.

Overrides:

backward in class MemoryLayer

Parameters:

pattern - double[] - input pattern on wich to apply the transfer function

getDerivative

public double getDerivative(int i)

Similar to the backward message and used by RTRL

Specified by:

getDerivative in class Layer

forward

protected void forward(double[] pattern)

Description copied from class: MemoryLayer

Transfer function to recall a result on a trained net

Overrides:

forward in class MemoryLayer

Parameters:

pattern - double[] - input pattern

check

public java.util.TreeSet check()

Description copied from class: Layer

Get check messages from listeners. Subclasses should call this method from thier own check method.

Specified by:

check in interface NeuralLayer

Overrides:

check in class MemoryLayer

Returns:

validation errors.

See Also:

NeuralLayer

Inspections

public java.util.Collection Inspections()

It doesn't make sense to return biases for this layer

Specified by:

Inspections in interface Inspectable

Overrides:

Inspections in class Layer

Returns:

null

See Also:

org.joone.Inspection

getDefaultState

public double getDefaultState()

Description copied from class: Layer

Return the default state of a node in this layer, such as 0 for a tanh or 0.5 for a sigmoid layer

Specified by:

getDefaultState in class Layer

getMinimumState

public double getMinimumState()

Description copied from class: Layer

Return minimum value of a node in this layer

Specified by:

getMinimumState in class Layer

getMaximumState

public double getMaximumState()

Description copied from class: Layer

Return maximum value of a node in this layer

Specified by:

getMaximumState in class Layer