org.encog.neural.networks.synapse
Class DirectSynapse

java.lang.Object
  org.encog.persist.BasicPersistedSubObject
      org.encog.neural.networks.synapse.BasicSynapse
          org.encog.neural.networks.synapse.DirectSynapse

All Implemented Interfaces:

Serializable, Synapse, EncogPersistedObject

public class DirectSynapse
extends BasicSynapse

A direct synapse will present the entire input array to each of the directly connected neurons in the next layer. This layer type is useful when building a radial basis neural network. This synapse type is not teachable.

Author:

jheaton

See Also:

Serialized Form

Constructor Summary

DirectSynapse()
Simple default constructor.

DirectSynapse(Layer fromLayer, Layer toLayer)
Construct a direct synapse between the two specified layers.

Method Summary

Object	clone()
NeuralData	compute(NeuralData input) Compute the output from this synapse.
Persistor	createPersistor() Create a persistor for this type of synapse.
Matrix	getMatrix() Get the weight matrix.
int	getMatrixSize() Get the size of the matrix, or zero if one is not defined.
SynapseType	getType()
boolean	isTeachable()
void	setMatrix(Matrix matrix) Attempt to set the matrix for this layer.

Methods inherited from class org.encog.neural.networks.synapse.BasicSynapse

getFromLayer, getFromNeuronCount, getToLayer, getToNeuronCount, isSelfConnected, setFromLayer, setName, setToLayer, toString

Methods inherited from class org.encog.persist.BasicPersistedSubObject

getCollection, getDescription, getName, setCollection, setDescription

Methods inherited from class java.lang.Object

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

Methods inherited from interface org.encog.persist.EncogPersistedObject

getCollection, getDescription, getName, setCollection, setDescription

Constructor Detail

DirectSynapse

public DirectSynapse()

Simple default constructor.

DirectSynapse

public DirectSynapse(Layer fromLayer,
                     Layer toLayer)

Construct a direct synapse between the two specified layers.

Parameters:

fromLayer - The starting layer.

toLayer - The ending layer.

Method Detail

clone

public Object clone()

Specified by:

clone in interface Synapse

Specified by:

clone in class BasicSynapse

Returns:

A clone of this object.

compute

public NeuralData compute(NeuralData input)

Compute the output from this synapse.

Parameters:

input - The input to this synapse.

Returns:

The output is the same as the input.

createPersistor

public Persistor createPersistor()

Create a persistor for this type of synapse.

Returns:

A persistor.

getMatrix

public Matrix getMatrix()

Description copied from interface: Synapse

Get the weight matrix.

Returns:

null, this synapse type has no matrix.

getMatrixSize

public int getMatrixSize()

Description copied from interface: Synapse

Get the size of the matrix, or zero if one is not defined.

Returns:

0, this synapse type has no matrix.

getType

public SynapseType getType()

Returns:

The type of synapse that this is.

isTeachable

public boolean isTeachable()

Returns:

False, because this type of synapse is not teachable.

setMatrix

public void setMatrix(Matrix matrix)

Attempt to set the matrix for this layer. This will throw an error, because this layer type does not have a matrix.

Parameters:

matrix - Not used.