org.encog.examples.neural.benchmark
Class FahlmanEncoder

java.lang.Object
  org.encog.examples.neural.benchmark.FahlmanEncoder

public class FahlmanEncoder
extends Object

This example implements a Fahlman Encoder. Though probably not invented by Scott Fahlman, such encoders were used in many of his papers, particularly: "An Empirical Study of Learning Speed in Backpropagation Networks" (Fahlman,1988) It provides a very simple way of evaluating classification neural networks. Basically, the input and output neurons are the same in count. However, there is a smaller number of hidden neurons. This forces the neural network to learn to encode the patterns from the input neurons to a smaller vector size, only to be expanded again to the outputs. The training data is exactly the size of the input/output neuron count. Each training element will have a single column set to 1 and all other columns set to zero. You can also perform in "complement mode", where the opposite is true. In "complement mode" all columns are set to 1, except for one column that is 0. The data produced in "complement mode" is more difficult to train. Fahlman used this simple training data to benchmark neural networks when he introduced the Quickprop algorithm in the above paper.

Field Summary

static boolean	COMPL
static int	HIDDEN_COUNT
static int	INPUT_OUTPUT_COUNT
static int	TRIES

Constructor Summary

FahlmanEncoder()

Method Summary

static void	evaluate()
static org.encog.ml.data.MLDataSet	generateTraining(int inputCount, boolean compl)
static void	main(String[] args)

Methods inherited from class java.lang.Object

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

Field Detail

INPUT_OUTPUT_COUNT

public static final int INPUT_OUTPUT_COUNT

See Also:

Constant Field Values

HIDDEN_COUNT

public static final int HIDDEN_COUNT

See Also:

Constant Field Values

TRIES

public static final int TRIES

See Also:

Constant Field Values

COMPL

public static final boolean COMPL

See Also:

Constant Field Values

Constructor Detail

FahlmanEncoder

public FahlmanEncoder()

Method Detail

generateTraining

public static org.encog.ml.data.MLDataSet generateTraining(int inputCount,
                                                           boolean compl)

evaluate

public static void evaluate()

main

public static void main(String[] args)