Package libai.nn.unsupervised

Class UnsupervisedLearning

java.lang.Object

libai.nn.NeuralNetwork

libai.nn.unsupervised.UnsupervisedLearning

All Implemented Interfaces:

java.io.Serializable

Direct Known Subclasses:

Competitive, Hopfield, Kohonen

public abstract class UnsupervisedLearning
extends NeuralNetwork

Created by kronenthaler on 19/03/2017.

See Also:

Serialized Form

Field Summary

Fields inherited from class libai.nn.NeuralNetwork

plotter, progress, random

Constructor Summary

Constructors

Constructor	Description
UnsupervisedLearning()
UnsupervisedLearning(java.util.Random rand)

Method Summary

Modifier and Type	Method	Description
abstract void	train(Column[] patterns, double alpha, int epochs, int offset, int length)	Trains this neural network with the list of patterns and the expected answers.
void	train(Column[] patterns, Column[] answers, double alpha, int epochs, int offset, int length, double minerror)	Trains this neural network with the list of patterns and the expected answers.
protected void	validatePreconditions(Column[] patterns, int epochs, int offset, int length)

Methods inherited from class libai.nn.NeuralNetwork

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

Methods inherited from class java.lang.Object

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

Constructor Detail

UnsupervisedLearning

public UnsupervisedLearning()

UnsupervisedLearning

public UnsupervisedLearning(java.util.Random rand)

Method Detail

train

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

Trains this neural network with the list of patterns and the expected answers.

Use the learning rate alpha for many epochs. Take length patterns from the position offset.

patterns must be array of non-null column matrices

Parameters:

patterns - The patterns to be learned.

alpha - The learning rate.

epochs - The maximum number of iterations

offset - The first pattern position

length - How many patterns will be used.

train

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

Description copied from class: NeuralNetwork

Trains this neural network with the list of patterns and the expected answers.

Use the learning rate alpha for many epochs. Take length patterns from the position offset until the minerror is reached.

patterns and answers must be arrays of non-null column matrices

Specified by:

train in class NeuralNetwork

Parameters:

patterns - The patterns to be learned.

answers - The expected answers.

alpha - The learning rate.

epochs - The maximum number of iterations

offset - The first pattern position

length - How many patterns will be used.

minerror - The minimal error expected.

validatePreconditions

protected void validatePreconditions(Column[] patterns,
                                     int epochs,
                                     int offset,
                                     int length)