org.encog.neural.networks.training.propagation.manhattan
Class ManhattanPropagationMethod

java.lang.Object
  org.encog.neural.networks.training.propagation.manhattan.ManhattanPropagationMethod

All Implemented Interfaces:

PropagationMethod

public class ManhattanPropagationMethod
extends java.lang.Object
implements PropagationMethod

Implements the specifics of the Manhattan propagation algorithm. This class actually handles the updates to the weight matrix.

Author:

jheaton

Constructor Summary

ManhattanPropagationMethod()

Method Summary

void	calculateError(NeuralOutputHolder output, PropagationLevel fromLevel, PropagationLevel toLevel) Calculate the error between these two levels.
void	init(Propagation propagation) Init with the specified propagation object.
void	learn() Modify the weight matrix and thresholds based on the last call to calcError.

Methods inherited from class java.lang.Object

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

Constructor Detail

ManhattanPropagationMethod

public ManhattanPropagationMethod()

Method Detail

calculateError

public void calculateError(NeuralOutputHolder output,
                           PropagationLevel fromLevel,
                           PropagationLevel toLevel)

Calculate the error between these two levels.

Specified by:

calculateError in interface PropagationMethod

Parameters:

output - The output to the "to level".

fromLevel - The from level.

toLevel - The target level.

init

public void init(Propagation propagation)

Init with the specified propagation object.

Specified by:

init in interface PropagationMethod

Parameters:

propagation - The propagation object that this method will be used with.

learn

public void learn()

Modify the weight matrix and thresholds based on the last call to calcError.

Specified by:

learn in interface PropagationMethod