org.encog.neural.networks.layers
Class HopfieldLayer

java.lang.Object
  org.encog.neural.networks.layers.BasicLayer
      org.encog.neural.networks.layers.HopfieldLayer

All Implemented Interfaces:

Layer, EncogPersistedObject

public class HopfieldLayer
extends BasicLayer
implements EncogPersistedObject

HopfieldLayer: This class implements a Hopfield neural network. A Hopfield neural network is fully connected and consists of a single layer. Hopfield neural networks are usually used for pattern recognition.

Constructor Summary

HopfieldLayer(int size)
Construct a hopfield layer of the specified size.

Method Summary

NeuralData	compute(NeuralData pattern) Present a pattern to the neural network and receive the result.
BiPolarNeuralData	getFire() Get the output array from the last time that the output of this layer was calculated.

Methods inherited from class org.encog.neural.networks.layers.BasicLayer

getFire, getMatrix, getMatrixSize, getNeuronCount, getNext, getPrevious, hasMatrix, isHidden, isInput, isOutput, reset, setFire, setFire, setMatrix, setNext, setPrevious

Methods inherited from class java.lang.Object

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

Constructor Detail

HopfieldLayer

public HopfieldLayer(int size)

Construct a hopfield layer of the specified size.

Parameters:

size - The number of neurons in this layer.

Method Detail

compute

public NeuralData compute(NeuralData pattern)

Present a pattern to the neural network and receive the result.

Specified by:

compute in interface Layer

Overrides:

compute in class BasicLayer

Parameters:

pattern - The pattern to be presented to the neural network.

Returns:

The output from the neural network.

getFire

public BiPolarNeuralData getFire()

Description copied from class: BasicLayer

Get the output array from the last time that the output of this layer was calculated.

Specified by:

getFire in interface Layer

Overrides:

getFire in class BasicLayer

Returns:

Get the fire data.