org.encog.neural.networks.structure

Class NeuralStructure

java.lang.Object

org.encog.neural.networks.structure.NeuralStructure

All Implemented Interfaces:

java.io.Serializable

public class NeuralStructure
extends java.lang.Object
implements java.io.Serializable

Holds "cached" information about the structure of the neural network. This is a very good performance boost since the neural network does not need to traverse itself each time a complete collection of layers or synapses is needed.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
NeuralStructure(BasicNetwork network) Construct a structure object for the specified network.

Method Summary

Modifier and Type	Method and Description
int	calculateSize() Calculate the size that an array should be to hold all of the weights and bias values.
void	enforceLimit() Enforce that all connections are above the connection limit.
void	finalizeLimit() Parse/finalize the limit value for connections.
void	finalizeStructure()
void	finalizeStructure(boolean dropout) Build the synapse and layer structure.
double	getConnectionLimit()
FlatNetwork	getFlat()
java.util.List<Layer>	getLayers()
BasicNetwork	getNetwork()
boolean	isConnectionLimited()
void	requireFlat() Throw an error if there is no flat network.
void	setFlat(FlatNetwork flat) Set the flat network.
void	updateProperties() Update any properties from the property map.

Methods inherited from class java.lang.Object

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

Constructor Detail

NeuralStructure

public NeuralStructure(BasicNetwork network)

Construct a structure object for the specified network.

Parameters:

network - The network to construct a structure for.

Method Detail

calculateSize

public final int calculateSize()

Calculate the size that an array should be to hold all of the weights and bias values.

Returns:

The size of the calculated array.

enforceLimit

public final void enforceLimit()

Enforce that all connections are above the connection limit. Any connections below this limit will be severed.

finalizeLimit

public void finalizeLimit()

Parse/finalize the limit value for connections.

finalizeStructure

public final void finalizeStructure(boolean dropout)

Build the synapse and layer structure. This method should be called after you are done adding layers to a network, or change the network's logic property.

Parameters:

dropout - Is dropout used?

finalizeStructure

public final void finalizeStructure()

getConnectionLimit

public final double getConnectionLimit()

Returns:

The connection limit.

getFlat

public final FlatNetwork getFlat()

Returns:

The flat network.

getLayers

public final java.util.List<Layer> getLayers()

Returns:

The layers in this neural network.

getNetwork

public final BasicNetwork getNetwork()

Returns:

The network this structure belongs to.

isConnectionLimited

public final boolean isConnectionLimited()

Returns:

True if this is not a fully connected feedforward network.

requireFlat

public final void requireFlat()

Throw an error if there is no flat network.

setFlat

public final void setFlat(FlatNetwork flat)

Set the flat network.

Parameters:

flat - The flat network.

updateProperties

public final void updateProperties()

Update any properties from the property map.