org.joone.engine

Class WTALayer

java.lang.Object

org.joone.engine.Layer

org.joone.engine.SimpleLayer

org.joone.engine.WTALayer

All Implemented Interfaces:

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

public class WTALayer
extends SimpleLayer

This layer implements the Winner Takes All SOM strategy. The layer expects to receive euclidean distances between the previous synapse weights and it's input. The layer simply works out which node is the winner and passes 1.0 for that node and 0.0 for the others.

See Also:

parent, Serialized Form

Field Summary

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

Constructors

Constructor and Description
WTALayer() The default constructor for this WTALayer.
WTALayer(java.lang.String ElemName) The constructor allowing a name to be specified.

Method Summary

Methods

Modifier and Type	Method and Description
void	backward(double[] pattern) No biases need updating or setting.
java.util.TreeSet	check() Check that there are no errors or problems with the properties of this WTALayer.
void	forward(double[] pattern) This method accepts an array of values from the input and forwards it according to the Winner Takes All strategy.
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
int	getLayerDepth() Getter for property LayerDepth.
int	getLayerHeight() Getter for property LayerHeight.
int	getLayerWidth() Getter for property LayerWidth.
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
void	setLayerDepth(int layerDepth) Setter for property layerDepth.
void	setLayerHeight(int LayerHeight) Setter for property LayerHeight.
void	setLayerWidth(int LayerWidth) Setter for property LayerWidth.

Methods inherited from class org.joone.engine.SimpleLayer

getLearningRate, getLrate, getMomentum, setDimensions, setLrate, setMomentum, setMonitor

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, getDimension, 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, setOutputDimension, setOutputSynapses, setRows, start, stop, sumBackInput, sumInput, toString

Methods inherited from class java.lang.Object

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

Constructor Detail

WTALayer

public WTALayer()

The default constructor for this WTALayer.

WTALayer

public WTALayer(java.lang.String ElemName)

The constructor allowing a name to be specified.

Parameters:

ElemName - The name of the Layer

Method Detail

backward

public void backward(double[] pattern)
              throws JooneRuntimeException

No biases need updating or setting. Not implemented / not required.

Overrides:

backward in class SimpleLayer

Parameters:

pattern - The pattern with which to update internal variables. Not required.

Throws:

JooneRuntimeException - The Joone Run time exception.

getDerivative

public double getDerivative(int i)

Similar to the backward message and used by RTRL

Specified by:

getDerivative in class Layer

forward

public void forward(double[] pattern)
             throws JooneRuntimeException

This method accepts an array of values from the input and forwards it according to the Winner Takes All strategy. See class documentation.

Specified by:

forward in class Layer

Parameters:

pattern -

Should be the euclidean distance between the previous synapse's input vector and weights.

Throws:

JooneRuntimeException - This Exception is a wrapper Exception when an Exception is thrown while doing the maths.

See Also:

(double[])

getLayerDepth

public int getLayerDepth()

Getter for property LayerDepth.

Returns:

Value of property LayerDepth.

setLayerDepth

public void setLayerDepth(int layerDepth)

Setter for property layerDepth.

Parameters:

LayerDepth - New value of property layerDepth.

getLayerHeight

public int getLayerHeight()

Getter for property LayerHeight.

Returns:

Value of property LayerHeight.

setLayerHeight

public void setLayerHeight(int LayerHeight)

Setter for property LayerHeight.

Parameters:

LayerHeight - New value of property LayerHeight.

getLayerWidth

public int getLayerWidth()

Getter for property LayerWidth.

Returns:

Value of property LayerWidth.

setLayerWidth

public void setLayerWidth(int LayerWidth)

Setter for property LayerWidth.

Parameters:

LayerWidth - New value of property LayerWidth.

check

public java.util.TreeSet check()

Check that there are no errors or problems with the properties of this WTALayer.

Specified by:

check in interface NeuralLayer

Overrides:

check in class Layer

Returns:

The TreeSet of errors / problems if any.

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