weka.classifiers.neural
Class NeuralNode

java.lang.Object
  |
  +--weka.classifiers.neural.NeuralConnection
        |
        +--weka.classifiers.neural.NeuralNode

All Implemented Interfaces:

java.io.Serializable

public class NeuralNode

extends NeuralConnection

This class is used to represent a node in the neuralnet.

Author:

Malcolm Ware (mfw4@cs.waikato.ac.nz)

See Also:

Serialized Form

Fields inherited from class weka.classifiers.neural.NeuralConnection

CONNECTED, INPUT, m_id, m_inputList, m_inputNums, m_numInputs, m_numOutputs, m_outputList, m_outputNums, m_type, m_unitError, m_unitValue, m_weightsUpdated, m_x, m_y, OUTPUT, PURE_INPUT, PURE_OUTPUT, UNCONNECTED

Constructor Summary

NeuralNode(java.lang.String id, java.util.Random r, NeuralMethod m)

Method Summary

protected void	allocateInputs() This will allocate more space for input connection information if the arrays for this have been filled up.
protected boolean	connectInput(NeuralConnection i, int n) This will connect the specified unit to be an input to this unit.
protected boolean	disconnectInput(NeuralConnection i, int n) This will disconnect the input with the specific connection number From this node (only on this end however).
double	errorValue(boolean calculate) Call this to get the error value of this unit.
double[]	getChangeInWeights() call this function to get the chnage in weights array.
NeuralMethod	getMethod()
double[]	getWeights() call this function to get the weights array.
double	outputValue(boolean calculate) Call this to get the output value of this unit.
void	removeAllInputs() This function will remove all the inputs to this unit.
void	reset() Call this to reset the value and error for this unit, ready for the next run.
void	setMethod(NeuralMethod m) Set how this node should operate (note that the neural method has no internal state, so the same object can be used by any number of nodes.
void	updateWeights(double l, double m) Call this function to update the weight values at this unit.
double	weightValue(int n) Call this to get the weight value on a particular connection.

Methods inherited from class weka.classifiers.neural.NeuralConnection

allocateOutputs, changeInputNum, changeOutputNum, connect, connectOutput, disconnect, disconnectOutput, drawHighlight, drawInputLines, drawNode, drawOutputLines, getId, getInputNums, getInputs, getNumInputs, getNumOutputs, getOutputNums, getOutputs, getType, getX, getY, onUnit, removeAllOutputs, setType, setX, setY

Methods inherited from class java.lang.Object

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

Constructor Detail

NeuralNode

public NeuralNode(java.lang.String id,
                  java.util.Random r,
                  NeuralMethod m)

Parameters:

id - The string name for this node (used to id this node).

r - A random number generator used to generate initial weights.

m - The methods this node should use to update.

Method Detail

setMethod

public void setMethod(NeuralMethod m)

Set how this node should operate (note that the neural method has no internal state, so the same object can be used by any number of nodes.

Parameters:

m - The new method.

getMethod

public NeuralMethod getMethod()

outputValue

public double outputValue(boolean calculate)

Call this to get the output value of this unit.

Overrides:

outputValue in class NeuralConnection

Parameters:

calculate - True if the value should be calculated if it hasn't been already.

Returns:

The output value, or NaN, if the value has not been calculated.

errorValue

public double errorValue(boolean calculate)

Call this to get the error value of this unit.

Overrides:

errorValue in class NeuralConnection

Parameters:

calculate - True if the value should be calculated if it hasn't been already.

Returns:

The error value, or NaN, if the value has not been calculated.

reset

public void reset()

Call this to reset the value and error for this unit, ready for the next run. This will also call the reset function of all units that are connected as inputs to this one. This is also the time that the update for the listeners will be performed.

Overrides:

reset in class NeuralConnection

weightValue

public double weightValue(int n)

Call this to get the weight value on a particular connection.

Overrides:

weightValue in class NeuralConnection

Parameters:

n - The connection number to get the weight for, -1 if The threshold weight should be returned.

Returns:

The value for the specified connection or if -1 then it should return the threshold value. If no value exists for the specified connection, NaN will be returned.

getWeights

public double[] getWeights()

call this function to get the weights array. This will also allow the weights to be updated.

Returns:

The weights array.

getChangeInWeights

public double[] getChangeInWeights()

call this function to get the chnage in weights array. This will also allow the change in weights to be updated.

Returns:

The change in weights array.

updateWeights

public void updateWeights(double l,
                          double m)

Call this function to update the weight values at this unit. After the weights have been updated at this unit, All the input connections will then be called from this to have their weights updated.

Overrides:

updateWeights in class NeuralConnection

Parameters:

l - The learning rate to use.

m - The momentum to use.

connectInput

protected boolean connectInput(NeuralConnection i,
                               int n)

This will connect the specified unit to be an input to this unit.

Overrides:

connectInput in class NeuralConnection

Parameters:

i - The unit.

n - It's connection number for this connection.

Returns:

True if the connection was made, false otherwise.

allocateInputs

protected void allocateInputs()

This will allocate more space for input connection information if the arrays for this have been filled up.

Overrides:

allocateInputs in class NeuralConnection

disconnectInput

protected boolean disconnectInput(NeuralConnection i,
                                  int n)

This will disconnect the input with the specific connection number From this node (only on this end however).

Overrides:

disconnectInput in class NeuralConnection

Parameters:

i - The unit to disconnect.

n - The connection number at the other end, -1 if all the connections to this unit should be severed (not the same as removeAllInputs).

Returns:

True if the connection was removed, false if the connection was not found.

removeAllInputs

public void removeAllInputs()

This function will remove all the inputs to this unit. In doing so it will also terminate the connections at the other end.

Overrides:

removeAllInputs in class NeuralConnection