org.encog.neural.networks.logic
Class FeedforwardLogic

java.lang.Object
  org.encog.neural.networks.logic.FeedforwardLogic

All Implemented Interfaces:

Serializable, NeuralLogic

Direct Known Subclasses:

SimpleRecurrentLogic

public class FeedforwardLogic
extends Object
implements NeuralLogic

Provides the neural logic for an Feedforward type network. See FeedforwardPattern for more information on this type of network.

See Also:

Serialized Form

Constructor Summary

FeedforwardLogic()

Method Summary

NeuralData	compute(NeuralData input, NeuralOutputHolder useHolder) Compute the output for a given input to the neural network.
BasicNetwork	getNetwork()
void	init(BasicNetwork network) Setup the network logic, read parameters from the network.
void	preprocessLayer(Layer layer, NeuralData input, Synapse source) Can be overridden by subclasses.

Methods inherited from class java.lang.Object

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

Constructor Detail

FeedforwardLogic

public FeedforwardLogic()

Method Detail

compute

public NeuralData compute(NeuralData input,
                          NeuralOutputHolder useHolder)

Compute the output for a given input to the neural network. This method provides a parameter to specify an output holder to use. This holder allows propagation training to track the output from each layer. If you do not need this holder pass null, or use the other compare method.

Specified by:

compute in interface NeuralLogic

Parameters:

input - The input provide to the neural network.

useHolder - Allows a holder to be specified, this allows propagation training to check the output of each layer.

Returns:

The results from the output neurons.

getNetwork

public BasicNetwork getNetwork()

Returns:

The network in use.

init

public void init(BasicNetwork network)

Setup the network logic, read parameters from the network.

Specified by:

init in interface NeuralLogic

Parameters:

network - The network that this logic class belongs to.

preprocessLayer

public void preprocessLayer(Layer layer,
                            NeuralData input,
                            Synapse source)

Can be overridden by subclasses. Usually used to implement recurrent layers.

Parameters:

layer - The layer to process.

input - The input to this layer.

source - The source from this layer.