org.encog.neural.networks.training.propagation
Class PropagationUtil

java.lang.Object
  org.encog.neural.networks.training.propagation.PropagationUtil

public class PropagationUtil
extends java.lang.Object

Provides basic functionality for all of the propagation types.

Constructor Summary

PropagationUtil(BasicNetwork network, PropagationMethod method)
Construct a propagation utility.

Method Summary

void	backwardPass(NeuralData ideal) Calculate the error for the recognition just done.
NeuralData	forwardPass(NeuralData input) Perform the forward pass and determine each layer's output.
java.util.List<PropagationLevel>	getLevels()
PropagationMethod	getMethod()
BasicNetwork	getNetwork() Get the current best neural network.
NeuralOutputHolder	getOutputHolder()

Methods inherited from class java.lang.Object

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

Constructor Detail

PropagationUtil

public PropagationUtil(BasicNetwork network,
                       PropagationMethod method)

Construct a propagation utility.

Parameters:

network - The network to train.

method - The method to use.

Method Detail

backwardPass

public void backwardPass(NeuralData ideal)

Calculate the error for the recognition just done.

Parameters:

ideal - What the output neurons should have yielded.

forwardPass

public NeuralData forwardPass(NeuralData input)

Perform the forward pass and determine each layer's output.

Parameters:

input - The input to the neural network.

Returns:

The output from the neural network.

getLevels

public java.util.List<PropagationLevel> getLevels()

Returns:

The propagation levels.

getMethod

public PropagationMethod getMethod()

Returns:

The propagation method in use.

getNetwork

public BasicNetwork getNetwork()

Get the current best neural network.

Returns:

The current best neural network.

getOutputHolder

public NeuralOutputHolder getOutputHolder()

Returns:

The output holder being used.