org.joone.engine
Class MemoryLayer

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

All Implemented Interfaces:

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

Direct Known Subclasses:

DelayLayer

public abstract class MemoryLayer
extends Layer

See Also:

Serialized Form

Field Summary

protected double[]	backmemory
protected double[]	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

MemoryLayer()

MemoryLayer(java.lang.String ElemName)

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
int	getDimension() Returns the number of neurons contained in the layer
int	getTaps() Return the taps value (06/04/00 1.08.26)
protected void	setDimensions() Sets the dimension of the layer.
protected void	setOutputDimension(OutputPatternListener syn) Sets the dimansion of the output (22/03/00 1.45.24)
void	setTaps(int newTaps) Inserire qui la descrizione del metodo.
protected void	sumBackInput(double[] pattern) Calculates the net input of the error gradents during the learning phase

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, getDefaultState, getDerivative, getLastGradientInps, getLastGradientOuts, getLastInputs, getLastOutputs, getLayerName, getLearner, getMaximumState, getMinimumState, getMonitor, getRows, getThreadMonitor, hasStepCounter, init, initLearner, InspectableTitle, Inspections, 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

Field Detail

memory

protected double[] memory

backmemory

protected double[] backmemory

Constructor Detail

MemoryLayer

public MemoryLayer()

MemoryLayer

public MemoryLayer(java.lang.String ElemName)

Method Detail

getDimension

public int getDimension()

Description copied from class: Layer

Returns the number of neurons contained in the layer

Overrides:

getDimension in class Layer

Returns:

the number of neurons in the layer.

getTaps

public int getTaps()

Return the taps value (06/04/00 1.08.26)

Returns:

int

setDimensions

protected void setDimensions()

Description copied from class: Layer

Sets the dimension of the layer. Override to define how the internal buffers must be sized.

Specified by:

setDimensions in class Layer

setOutputDimension

protected void setOutputDimension(OutputPatternListener syn)

Sets the dimansion of the output (22/03/00 1.45.24)

Overrides:

setOutputDimension in class Layer

Parameters:

syn - neural.engine.Synapse

setTaps

public void setTaps(int newTaps)

Inserire qui la descrizione del metodo. Data di creazione: (06/04/00 1.08.26)

Parameters:

newTaps - int

sumBackInput

protected void sumBackInput(double[] pattern)

Description copied from class: Layer

Calculates the net input of the error gradents during the learning phase

Overrides:

sumBackInput in class Layer

Parameters:

pattern - array of input values

backward

protected void backward(double[] pattern)

Reverse transfer function of the component.

Specified by:

backward in class Layer

Parameters:

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

forward

protected void forward(double[] pattern)

Transfer function to recall a result on a trained net

Specified by:

forward in class Layer

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 Layer

Returns:

validation errors.

See Also:

NeuralLayer