SciLib.Neuro
Class Madaline

java.lang.Object
  SciLib.Neuro.Nnet
      SciLib.Neuro.Madaline

public class Madaline
extends Nnet

This class defines A Madeline Network.

Field Summary

Fields inherited from class SciLib.Neuro.Nnet

averageError, DesiredOutputMatrix, errorThreshold, g, hidden, hiddenSize, inSize, learningRate, momentum, numberOfHiddenLayers, NumberOfTestPatterns, NumberOfTrainingPatterns, output, outSize, testingData, testingDesiredOutput, trainingData, trainingDesiredOutput

Constructor Summary

Madaline(int is, int os, Activation phi)
Make A Madeline network with specific size and activation function

Method Summary

void	computeOutput(vector x) Compute output
void	setup()
java.lang.String	testing() Testing A Madaline network
void	training(double epsi, double eta) Training a Madaline network

Methods inherited from class SciLib.Neuro.Nnet

generate, getErrorThreshold, getHiddenLayers, gethiddenSize, getInputSize, getLearningRate, getMomentumPar, getnumberOfHiddenLayers, getNumberOfTestPatterns, getNumberOfTrainingPatterns, getOutputLayer, getOutputSize, getTrainingData, getTrainingDesiredOutput, makeDesiredOutputMatrix, makeDesiredOutputMatrix, makeTrainingSet, readTestingData, readTrainingData, readWeight, setActivation, setErrorThreshold, setInputSize, setLearningRate, setMomentumPar, setNumberOfTestPatterns, setNumberOfTrainingPatterns, setOutputSize, setSize, writeWeight

Methods inherited from class java.lang.Object

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

Constructor Detail

Madaline

public Madaline(int is,
                int os,
                Activation phi)

Make A Madeline network with specific size and activation function

Parameters:

is - An integer value, the input size

os - An integer value, the output size

phi - An Activation object

Method Detail

setup

public void setup()

computeOutput

public void computeOutput(vector x)

Compute output

training

public void training(double epsi,
                     double eta)

Training a Madaline network

Parameters:

epsi - The tolerance error

eta - The learning rate

testing

public java.lang.String testing()

Testing A Madaline network