Package libai.nn.unsupervised

Class Hopfield

java.lang.Object

libai.nn.NeuralNetwork

libai.nn.unsupervised.UnsupervisedLearning

libai.nn.unsupervised.Hopfield

All Implemented Interfaces:

java.io.Serializable

public class Hopfield
extends UnsupervisedLearning

Hopfield's networks are the most important and most applicable recurrent neural network. This Hopfield networks uses an deterministic unsupervised training algorithm and a bipolar encoding for the training patterns and answers. As the Hebb network this network is a associative memory. The main goal of this network is memorize and retrieve the memorized patterns without noise.

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field	Description
protected static SymmetricSign	ssign
protected Matrix	W

Fields inherited from class libai.nn.NeuralNetwork

plotter, progress, random

Constructor Summary

Constructors

Constructor	Description
Hopfield(int inputs)	Constructor.

Method Summary

Modifier and Type	Method	Description
Column	simulate(Column pattern)	Calculates the output for the pattern.
void	simulate(Column pattern, Column result)	Calculates the output for the pattern and left the result in result.
void	train(Column[] patterns, double alpha, int epochs, int offset, int length)	Train the network.

Methods inherited from class libai.nn.NeuralNetwork

error, error, euclideanDistance2, euclideanDistance2, gaussian, getDefaultRandomGenerator, getPlotter, getProgressBar, initializeProgressBar, open, open, open, save, setPlotter, setProgressBar, train, train

Methods inherited from class java.lang.Object

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

Methods inherited from class libai.nn.unsupervised.UnsupervisedLearning

train, validatePreconditions

Field Detail

ssign

protected static final SymmetricSign ssign

W

protected final Matrix W

Constructor Detail

Hopfield

public Hopfield(int inputs)

Constructor. Receives the number of input to the network.

Parameters:

inputs - The number of input to the network.

Method Detail

train

public void train(Column[] patterns,
                  double alpha,
                  int epochs,
                  int offset,
                  int length)

Train the network. The answers, alpha, epochs and minerror are meaningless in this algorithm.

Specified by:

train in class UnsupervisedLearning

Parameters:

patterns - The patterns to be learned.

alpha - The learning rate. [ignored]

epochs - The maximum number of iterations. [ignored]

offset - The first pattern position.

length - How many patterns will be used.

simulate

public Column simulate(Column pattern)

Description copied from class: NeuralNetwork

Calculates the output for the pattern.

Specified by:

simulate in class NeuralNetwork

Parameters:

pattern - Pattern to use as input.

Returns:

The output for the neural network.

simulate

public void simulate(Column pattern,
                     Column result)

Description copied from class: NeuralNetwork

Calculates the output for the pattern and left the result in result.

Specified by:

simulate in class NeuralNetwork

Parameters:

pattern - Pattern to use as input.

result - The output for the input.