Java Code Examples for org.neuroph.nnet.MultiLayerPerceptron#setLearningRule()

@Test
public void testXorMSE() {
    MultiLayerPerceptron myMlPerceptron = new MultiLayerPerceptron(TransferFunctionType.SIGMOID, 2, 3, 1);
    myMlPerceptron.randomizeWeights(new WeightsRandomizer(new Random(123)));

    myMlPerceptron.setLearningRule(instance);
    myMlPerceptron.learn(xorDataSet);

    MeanSquaredError mse = new MeanSquaredError();
    for (DataSetRow testSetRow : xorDataSet.getRows()) {
        myMlPerceptron.setInput(testSetRow.getInput());
        myMlPerceptron.calculate();
        double[] networkOutput = myMlPerceptron.getOutput();
        mse.addPatternError(networkOutput, testSetRow.getDesiredOutput());
    }
    assertTrue(mse.getTotalError() < maxError);
}
 

@Test
public void testXorMSE() {
    MultiLayerPerceptron myMlPerceptron = new MultiLayerPerceptron(TransferFunctionType.SIGMOID, 2, 3, 1);
    myMlPerceptron.randomizeWeights(new WeightsRandomizer(new Random(123)));

    myMlPerceptron.setLearningRule(instance);
    myMlPerceptron.learn(xorDataSet);

    MeanSquaredError mse = new MeanSquaredError();
    for (DataSetRow testSetRow : xorDataSet.getRows()) {
        myMlPerceptron.setInput(testSetRow.getInput());
        myMlPerceptron.calculate();
        double[] networkOutput = myMlPerceptron.getOutput();
        mse.addPatternError(networkOutput, testSetRow.getDesiredOutput());
    }
    assertTrue(mse.getTotalError() < maxError);
}
 

/**
 * Creates and returns a new instance of Multi Layer Perceptron
 * @param layersStr space separated number of neurons in layers
 * @param transferFunctionType transfer function type for neurons
 * @return instance of Multi Layer Perceptron
 */
public static MultiLayerPerceptron createMLPerceptron(String layersStr, TransferFunctionType transferFunctionType, Class learningRule,  boolean useBias, boolean connectIO) {
	ArrayList<Integer> layerSizes = VectorParser.parseInteger(layersStr);
               NeuronProperties neuronProperties = new NeuronProperties(transferFunctionType, useBias);
	MultiLayerPerceptron nnet = new MultiLayerPerceptron(layerSizes, neuronProperties);
               
               // set learning rule - TODO: use reflection here
               if (learningRule.getName().equals(BackPropagation.class.getName()))  {
                   nnet.setLearningRule(new BackPropagation());
               } else if (learningRule.getName().equals(MomentumBackpropagation.class.getName())) {
                   nnet.setLearningRule(new MomentumBackpropagation());
               } else if (learningRule.getName().equals(DynamicBackPropagation.class.getName())) {
                   nnet.setLearningRule(new DynamicBackPropagation());
               } else if (learningRule.getName().equals(ResilientPropagation.class.getName())) {
                   nnet.setLearningRule(new ResilientPropagation());
               } 

               // connect io
               if (connectIO) {
                   nnet.connectInputsToOutputs();
               }

	return nnet;
}
 

@Test
public void testXorMaxError() {
    MultiLayerPerceptron myMlPerceptron = new MultiLayerPerceptron(TransferFunctionType.SIGMOID, 2, 3, 1);
    myMlPerceptron.randomizeWeights(new WeightsRandomizer(new Random(123)));

    myMlPerceptron.setLearningRule(instance);
    myMlPerceptron.learn(xorDataSet);

    assertTrue(instance.getTotalNetworkError() < maxError);
}
 

@Test
public void testIrisMaxError() {
    MultiLayerPerceptron myMlPerceptron = new MultiLayerPerceptron(4, 16, 3);
    myMlPerceptron.randomizeWeights(new WeightsRandomizer(new Random(123)));
    myMlPerceptron.setLearningRule(instance);

    myMlPerceptron.learn(irisDataSet);

    assertTrue(instance.getTotalNetworkError() < maxError);
}
 

public void run() throws InterruptedException, ExecutionException {
    System.out.println("Creating training set...");
    // get path to training set
    String dataSetFile = "data_sets/wine.txt";
    int inputsCount = 11;
    int outputsCount = 10;

    // create training set from file
    DataSet dataSet = DataSet.createFromFile(dataSetFile, inputsCount, outputsCount, "\t", true);
    Normalizer norm = new MaxNormalizer(dataSet);
    norm.normalize(dataSet);
    dataSet.shuffle();

    System.out.println("Creating neural network...");
    MultiLayerPerceptron neuralNet = new MultiLayerPerceptron(inputsCount, 20, 15, outputsCount);

    neuralNet.setLearningRule(new MomentumBackpropagation());
    MomentumBackpropagation learningRule = (MomentumBackpropagation) neuralNet.getLearningRule();

    // set learning rate and max error
    learningRule.setLearningRate(0.1);
    learningRule.setMaxIterations(10);

    String classLabels[] = new String[]{"1", "2", "3", "4", "5", "6", "7", "8", "9", "10"};
    neuralNet.setOutputLabels(classLabels);
    KFoldCrossValidation crossVal = new KFoldCrossValidation(neuralNet, dataSet, 10);
    EvaluationResult totalResult= crossVal.run();
    List<FoldResult> cflist= crossVal.getResultsByFolds();
}
 

public void run() throws InterruptedException, ExecutionException {
    System.out.println("Creating training set...");
    // get path to training set
    String dataSetFile = "data_sets/seeds.txt";
    int inputsCount = 7;
    int outputsCount = 3;

    // create training set from file
    DataSet dataSet = DataSet.createFromFile(dataSetFile, inputsCount, outputsCount, "\t");
    dataSet.shuffle();

    System.out.println("Creating neural network...");
    MultiLayerPerceptron neuralNet = new MultiLayerPerceptron(inputsCount, 15, 2, outputsCount);

    neuralNet.setLearningRule(new MomentumBackpropagation());
    MomentumBackpropagation learningRule = (MomentumBackpropagation) neuralNet.getLearningRule();

    // set learning rate and max error
    learningRule.setLearningRate(0.1);
    learningRule.setMaxError(0.01);
    learningRule.setMaxIterations(1000);

    String[] classLabels = new String[]{"Cama", "Rosa", "Canadian"};
    neuralNet.setOutputLabels(classLabels);
    KFoldCrossValidation crossVal = new KFoldCrossValidation(neuralNet, dataSet, 10);
    EvaluationResult totalResult= crossVal.run();
     List<FoldResult> cflist= crossVal.getResultsByFolds();
}
 

public void run() {
    System.out.println("Creating training set...");
    // get path to training set
    String trainingSetFileName = "data_sets/abalonerings.txt";
    int inputsCount = 8;
    int outputsCount = 29;

    // create training set from file
    DataSet dataSet = DataSet.createFromFile(trainingSetFileName, inputsCount, outputsCount, "\t", true);

    // split data into train and test set
    DataSet[] trainTestSplit = dataSet.split(0.6, 0.4);
    DataSet trainingSet = trainTestSplit[0];
    DataSet testSet = trainTestSplit[1];

    // normalize data
    Normalizer norm = new MaxNormalizer(trainingSet);
    norm.normalize(trainingSet);
    norm.normalize(testSet);

    System.out.println("Creating neural network...");
    MultiLayerPerceptron neuralNet = new MultiLayerPerceptron(inputsCount, 15, 10, outputsCount);

    neuralNet.setLearningRule(new MomentumBackpropagation());
    MomentumBackpropagation learningRule = (MomentumBackpropagation) neuralNet.getLearningRule();
    learningRule.addListener(this);

    // set learning rate and max error
    learningRule.setLearningRate(0.1);
    learningRule.setMaxIterations(5000);

    System.out.println("Training network...");
    // train the network with training set
    neuralNet.learn(trainingSet);
    System.out.println("Training completed.");
    System.out.println("Testing network...");

    System.out.println("Network performance on the test set");
    evaluate(neuralNet, testSet);

    System.out.println("Saving network");
    // save neural network to file
    neuralNet.save("nn1.nnet");

    System.out.println("Done.");

    System.out.println();
    System.out.println("Network outputs for test set");
    testNeuralNetwork(neuralNet, testSet);
}
 

public void run() {
    System.out.println("Creating training set...");
    // get path to training set
    String trainingSetFileName = "data_sets/ionospheredata.txt";
    int inputsCount = 34;
    int outputsCount = 1;

    // create training set from file
    DataSet dataSet = DataSet.createFromFile(trainingSetFileName, inputsCount, outputsCount, ",", false);

    // split data into training and test set
    DataSet[] trainTestSplit = dataSet.split(0.6, 0.4);
    DataSet trainingSet = trainTestSplit[0];
    DataSet testSet = trainTestSplit[1];

    // normalize data
    Normalizer norm = new MaxNormalizer(trainingSet);
    norm.normalize(trainingSet);
    norm.normalize(testSet);

    System.out.println("Creating neural network...");
    MultiLayerPerceptron neuralNet = new MultiLayerPerceptron(inputsCount, 30, 25, outputsCount);

    neuralNet.setLearningRule(new MomentumBackpropagation());
    MomentumBackpropagation learningRule = (MomentumBackpropagation) neuralNet.getLearningRule();
    learningRule.addListener(this);

    // set learning rate and max error
    learningRule.setLearningRate(0.1);
    learningRule.setMaxError(0.01);
    System.out.println("Training network...");
    // train the network with training set
    neuralNet.learn(trainingSet);
    System.out.println("Training completed.");
    System.out.println("Testing network...");

    System.out.println("Network performance on the test set");
    evaluate(neuralNet, testSet);

    System.out.println("Saving network");
    // save neural network to file
    neuralNet.save("nn1.nnet");

    System.out.println("Done.");

    System.out.println();
    System.out.println("Network outputs for test set");
    testNeuralNetwork(neuralNet, testSet);
}
 

public void run() {
    System.out.println("Creating data set...");
    String dataSetFile = "data_sets/ml10standard/ionospheredata.txt";
    int inputsCount = 34;
    int outputsCount = 1;

    // create data set from file
    DataSet dataSet = DataSet.createFromFile(dataSetFile, inputsCount, outputsCount, ",", false);

    // split data into training and test set
    DataSet[] trainTestSplit = dataSet.split(0.6, 0.4);
    DataSet trainingSet = trainTestSplit[0];
    DataSet testSet = trainTestSplit[1];

    // normalize data
    Normalizer norm = new MaxNormalizer(trainingSet);
    norm.normalize(trainingSet);
    norm.normalize(testSet);

    System.out.println("Creating neural network...");
    MultiLayerPerceptron neuralNet = new MultiLayerPerceptron(inputsCount, 30, 25, outputsCount);

    neuralNet.setLearningRule(new MomentumBackpropagation());
    MomentumBackpropagation learningRule = (MomentumBackpropagation) neuralNet.getLearningRule();
    learningRule.addListener((event) -> {
        MomentumBackpropagation bp = (MomentumBackpropagation) event.getSource();
        System.out.println(bp.getCurrentIteration() + ". iteration | Total network error: " + bp.getTotalNetworkError());
    });

    // set learning rate and max error
    learningRule.setLearningRate(0.1);
    learningRule.setMaxError(0.01);
    System.out.println("Training network...");
    // train the network with training set
    neuralNet.learn(trainingSet);
    System.out.println("Training completed.");
    System.out.println("Testing network...");

    System.out.println("Network performance on the test set");
    evaluate(neuralNet, testSet);

    System.out.println("Saving network");
    // save neural network to file
    neuralNet.save("nn1.nnet");

    System.out.println("Done.");
}
 

public void run() {
    System.out.println("Creating training set...");
    // get path to training set
    String trainingSetFileName = "data_sets/sonardata.txt";
    int inputsCount = 60;
    int outputsCount = 1;

    // create training set from file
    DataSet dataSet = DataSet.createFromFile(trainingSetFileName, inputsCount, outputsCount, ",", false);

    // split data into train and test set
    DataSet[] trainTestSplit = dataSet.split(0.6, 0.4);
    DataSet trainingSet = trainTestSplit[0];
    DataSet testSet = trainTestSplit[1];

    // normalize data using max normalization
    Normalizer norm = new MaxNormalizer(trainingSet);
    norm.normalize(trainingSet);
    norm.normalize(testSet);

    System.out.println("Creating neural network...");
    MultiLayerPerceptron neuralNet = new MultiLayerPerceptron(inputsCount, 15, 10, outputsCount);

    neuralNet.setLearningRule(new MomentumBackpropagation());
    MomentumBackpropagation learningRule = (MomentumBackpropagation) neuralNet.getLearningRule();
    learningRule.addListener(this);

    // set learning rate and max error
    learningRule.setLearningRate(0.1);
    learningRule.setMaxError(0.01);
    System.out.println("Training network...");
    // train the network with training set
    neuralNet.learn(trainingSet);
    System.out.println("Training completed.");
    System.out.println("Testing network...");

    System.out.println("Network performance on the test set");
    evaluate(neuralNet, testSet);

    System.out.println("Saving network");
    // save neural network to file
    neuralNet.save("nn1.nnet");

    System.out.println("Done.");

    System.out.println();
    System.out.println("Network outputs for test set");
    testNeuralNetwork(neuralNet, testSet);
}
 

public void run() {
    System.out.println("Creating data set...");
    String dataSetFile = "data_sets/ml10standard/wine.txt";
    int inputsCount = 11;
    int outputsCount = 10;

    // create data set from file
    DataSet dataSet = DataSet.createFromFile(dataSetFile, inputsCount, outputsCount, "\t", true);

    // split data into train and test set
    DataSet[] trainTestSplit = dataSet.split(0.6, 0.4);
    DataSet trainingSet = trainTestSplit[0];
    DataSet testSet = trainTestSplit[1];

    Normalizer norm = new MaxNormalizer(trainingSet);
    norm.normalize(trainingSet);
    norm.normalize(testSet);

    System.out.println("Creating neural network...");
    MultiLayerPerceptron neuralNet = new MultiLayerPerceptron(inputsCount, 20, 15, outputsCount);

    neuralNet.setLearningRule(new MomentumBackpropagation());
    MomentumBackpropagation learningRule = (MomentumBackpropagation) neuralNet.getLearningRule();
    learningRule.addListener((event)->{
        MomentumBackpropagation bp = (MomentumBackpropagation) event.getSource();
        System.out.println(bp.getCurrentIteration() + ". iteration | Total network error: " + bp.getTotalNetworkError());
    });

    // set learning rate and max error
    learningRule.setLearningRate(0.1);
    learningRule.setMaxIterations(5000);

    System.out.println("Training network...");
    // train the network with training set
    neuralNet.learn(trainingSet);
    System.out.println("Training completed.");
    System.out.println("Testing network...");

    System.out.println("Network performance on the test set");
    evaluate(neuralNet, testSet);

    System.out.println("Saving network");
    // save neural network to file
    neuralNet.save("nn1.nnet");

    System.out.println("Done.");

    System.out.println();
    System.out.println("Network outputs for test set");
    testNeuralNetwork(neuralNet, testSet);
}
 

public void run() {
    String dataSetFile = "data_sets/ml10standard/sonardata.txt";
    int numInputs = 60;
    int numOutputs = 1;

    // create data set from csv file
    DataSet dataSet = DataSet.createFromFile(dataSetFile, numInputs, numOutputs, ",");

    // split data into train and test set
    DataSet[] trainTestSplit = dataSet.split(0.6, 0.4);
    DataSet trainingSet = trainTestSplit[0];
    DataSet testSet = trainTestSplit[1];

    // create neural network
    MultiLayerPerceptron neuralNet = new MultiLayerPerceptron(TransferFunctionType.TANH, numInputs, 35, 15, numOutputs);

    // set learning rule and add listener
    neuralNet.setLearningRule(new MomentumBackpropagation());
    MomentumBackpropagation learningRule = (MomentumBackpropagation) neuralNet.getLearningRule();
    learningRule.addListener((event) -> {
        MomentumBackpropagation bp = (MomentumBackpropagation) event.getSource();
        System.out.println(bp.getCurrentIteration() + ". iteration | Total network error: " + bp.getTotalNetworkError());
    });

    // set learning rate and max error
    learningRule.setLearningRate(0.01);
    learningRule.setMaxError(0.01);

    // train the network with training set
    neuralNet.learn(trainingSet);

    // evaluate network performance on test set
    evaluate(neuralNet, testSet);

    // save neural network to file
    neuralNet.save("nn1.nnet");

    System.out.println("Done.");

    //testNeuralNetwork(neuralNet, testSet);
}
 

public void run() {
    System.out.println("Creating data set...");
    String dataSetFile = "data_sets/ml10standard/abalonerings.txt";
    int inputsCount = 8;
    int outputsCount = 29;

    // create training set from file
    DataSet dataSet = DataSet.createFromFile(dataSetFile, inputsCount, outputsCount, "\t", true);
    DataSet[] trainTestSplit = dataSet.split(0.7, 0.3);
    DataSet trainingSet = trainTestSplit[0];
    DataSet testSet = trainTestSplit[1];

    Normalizer norm = new MaxNormalizer(trainingSet);
    norm.normalize(trainingSet);
    norm.normalize(testSet);

    System.out.println("Creating neural network...");
    MultiLayerPerceptron neuralNet = new MultiLayerPerceptron(inputsCount, 15, 10, outputsCount);

    neuralNet.setLearningRule(new MomentumBackpropagation());
    MomentumBackpropagation learningRule = (MomentumBackpropagation) neuralNet.getLearningRule();
    learningRule.addListener((event) -> {
        MomentumBackpropagation bp = (MomentumBackpropagation) event.getSource();
        System.out.println(bp.getCurrentIteration() + ". iteration | Total network error: " + bp.getTotalNetworkError());        
    });

    // set learning rate and max error
    learningRule.setLearningRate(0.1);
    learningRule.setMaxIterations(5000);

    System.out.println("Training network...");
    // train the network with training set
    neuralNet.learn(trainingSet);
    System.out.println("Training completed.");
    System.out.println("Testing network...");

    System.out.println("Network performance on the test set");
    evaluate(neuralNet, testSet);

    System.out.println("Saving network");
    // save neural network to file
    neuralNet.save("nn1.nnet");

    System.out.println("Done.");
}
 

public void run() {
    System.out.println("Creating training set...");
    // get path to training set
    String trainingSetFileName = "data_sets/seeds.txt";
    int inputsCount = 7;
    int outputsCount = 3;

    // create training set from file
    DataSet dataSet = DataSet.createFromFile(trainingSetFileName, inputsCount, outputsCount, "\t");

    // split data into train and test set
    DataSet[] trainTestSplit = dataSet.split(0.6, 0.4);
    DataSet trainingSet = trainTestSplit[0];
    DataSet testSet = trainTestSplit[1];

    System.out.println("Creating neural network...");
    MultiLayerPerceptron neuralNet = new MultiLayerPerceptron(inputsCount, 15, 2, outputsCount);

    neuralNet.setLearningRule(new MomentumBackpropagation());
    MomentumBackpropagation learningRule = (MomentumBackpropagation) neuralNet.getLearningRule();
    learningRule.addListener(this);

    // set learning rate and max error
    learningRule.setLearningRate(0.1);
    learningRule.setMaxError(0.01);
    learningRule.setMaxIterations(5000);
    System.out.println("Training network...");
    // train the network with training set
    neuralNet.learn(trainingSet);
    System.out.println("Training completed.");
    System.out.println("Testing network...");

    System.out.println("Network performance on the test set");
    evaluate(neuralNet, testSet);

    System.out.println("Saving network");
    // save neural network to file
    neuralNet.save("nn1.nnet");

    System.out.println("Done.");

    System.out.println();
    System.out.println("Network outputs for test set");
    testNeuralNetwork(neuralNet, testSet);
}
 

public void run() {
    System.out.println("Creating data set...");
    String dataSetFile = "data_sets/ml10standard/databanknote.txt";
    int inputsCount = 4;
    int outputsCount = 1;

    // create training set from file
    DataSet dataSet = DataSet.createFromFile(dataSetFile, inputsCount, outputsCount, ",", false);
    DataSet[] trainTestSplit = dataSet.split(0.6, 0.4);
    DataSet trainingSet = trainTestSplit[0];
    DataSet testSet = trainTestSplit[1];

    Normalizer norm = new MaxNormalizer(trainingSet);
    norm.normalize(trainingSet);
    norm.normalize(testSet);

    System.out.println("Creating neural network...");
    MultiLayerPerceptron neuralNet = new MultiLayerPerceptron(TransferFunctionType.TANH, inputsCount, 1, outputsCount);

    neuralNet.setLearningRule(new MomentumBackpropagation());
    MomentumBackpropagation learningRule = (MomentumBackpropagation) neuralNet.getLearningRule();
    learningRule.addListener((event) -> {
        MomentumBackpropagation bp = (MomentumBackpropagation) event.getSource();
        System.out.println(bp.getCurrentIteration() + ". iteration | Total network error: " + bp.getTotalNetworkError());
    });

    // set learning rate and max error
    learningRule.setLearningRate(0.1);
    learningRule.setMaxError(0.01);
    System.out.println("Training network...");
    // train the network with training set
    neuralNet.learn(trainingSet);
    System.out.println("Training completed.");
    System.out.println("Testing network...");

    System.out.println("Network performance on the test set");
    evaluate(neuralNet, testSet);

    System.out.println("Saving network");
    // save neural network to file
    neuralNet.save("nn1.nnet");

    System.out.println("Done.");
}
 

public void run() {
    System.out.println("Creating data set...");
    String dataSetFile = "data_sets/ml10standard/irisdatanormalised.txt";
    int inputsCount = 4;
    int outputsCount = 3;

    // create data set from file
    DataSet dataSet = DataSet.createFromFile(dataSetFile, inputsCount, outputsCount, ",");

    // split data into training and test set
    DataSet[] trainTestSplit = dataSet.split(0.6, 0.4);
    DataSet trainingSet = trainTestSplit[0];
    DataSet testSet = trainTestSplit[1];

    System.out.println("Creating neural network...");
    MultiLayerPerceptron neuralNet = new MultiLayerPerceptron(TransferFunctionType.TANH, inputsCount, 2, outputsCount);

    neuralNet.setLearningRule(new MomentumBackpropagation());
    MomentumBackpropagation learningRule = (MomentumBackpropagation) neuralNet.getLearningRule();
    learningRule.addListener((event)->{
        MomentumBackpropagation bp = (MomentumBackpropagation) event.getSource();
        System.out.println(bp.getCurrentIteration() + ". iteration | Total network error: " + bp.getTotalNetworkError());
    });

    // set learning rate and max error
    learningRule.setLearningRate(0.2);
    learningRule.setMaxError(0.03);
    System.out.println("Training network...");
    // train the network with training set
    neuralNet.learn(trainingSet);
    System.out.println("Training completed.");
    System.out.println("Testing network...");

    System.out.println("Network performance on the test set");
    evaluate(neuralNet, testSet);

    System.out.println("Saving network");
    // save neural network to file
    neuralNet.save("nn1.nnet");

    System.out.println("Done.");
}
 

/**
     * Runs this sample
     */
    public void run() {

        // create training set (logical XOR function)
        DataSet trainingSet = new DataSet(2, 1);
        trainingSet.add(new DataSetRow(new double[]{0, 0}, new double[]{0}));
        trainingSet.add(new DataSetRow(new double[]{0, 1}, new double[]{1}));
        trainingSet.add(new DataSetRow(new double[]{1, 0}, new double[]{1}));
        trainingSet.add(new DataSetRow(new double[]{1, 1}, new double[]{0}));

        // create multi layer perceptron
        MultiLayerPerceptron myMlPerceptron = new MultiLayerPerceptron(TransferFunctionType.SIGMOID, 2, 3, 1);
        myMlPerceptron.randomizeWeights(new WeightsRandomizer(new Random(123)));

        System.out.println(Arrays.toString(myMlPerceptron.getWeights()));

        myMlPerceptron.setLearningRule(new BackPropagation());

        myMlPerceptron.getLearningRule().setLearningRate(0.5);
        // enable batch if using MomentumBackpropagation
//        if( myMlPerceptron.getLearningRule() instanceof MomentumBackpropagation )
//        	((MomentumBackpropagation)myMlPerceptron.getLearningRule()).setBatchMode(false);

        LearningRule learningRule = myMlPerceptron.getLearningRule();
        learningRule.addListener(this);

        // learn the training set
        System.out.println("Training neural network...");
        myMlPerceptron.learn(trainingSet);

        // test perceptron
        System.out.println("Testing trained neural network");
        testNeuralNetwork(myMlPerceptron, trainingSet);

        // save trained neural network
        myMlPerceptron.save("myMlPerceptron.nnet");

        // load saved neural network
        NeuralNetwork loadedMlPerceptron = NeuralNetwork.createFromFile("myMlPerceptron.nnet");

        // test loaded neural network
        System.out.println("Testing loaded neural network");
        testNeuralNetwork(loadedMlPerceptron, trainingSet);
    }
 

public void run() {
    System.out.println("Creating training set...");
    // get path to training set
    String trainingSetFileName = "data_sets/irisdatanormalised.txt";
    int inputsCount = 4;
    int outputsCount = 3;

    // create training set from file
    DataSet dataSet = DataSet.createFromFile(trainingSetFileName, inputsCount, outputsCount, ",");

    // splid data into training and test set
    DataSet[] trainTestSplit = dataSet.split(0.6, 0.4);
    DataSet trainingSet = trainTestSplit[0];
    DataSet testSet = trainTestSplit[1];

    System.out.println("Creating neural network...");
    MultiLayerPerceptron neuralNet = new MultiLayerPerceptron(TransferFunctionType.TANH, inputsCount, 2, outputsCount);

    neuralNet.setLearningRule(new MomentumBackpropagation());
    MomentumBackpropagation learningRule = (MomentumBackpropagation) neuralNet.getLearningRule();
    learningRule.addListener(this);

    // set learning rate and max error
    learningRule.setLearningRate(0.2);
    learningRule.setMaxError(0.03);
    System.out.println("Training network...");
    // train the network with training set
    neuralNet.learn(trainingSet);
    System.out.println("Training completed.");
    System.out.println("Testing network...");

    System.out.println("Network performance on the test set");
    evaluate(neuralNet, testSet);

    System.out.println("Saving network");
    // save neural network to file
    neuralNet.save("nn1.nnet");

    System.out.println("Done.");

    System.out.println();
    System.out.println("Network outputs for test set");
    testNeuralNetwork(neuralNet, testSet);
}
 

public void run() {
    System.out.println("Creating training set...");
    // get path to training set
    String trainingSetFileName = "data_sets/pimadata.txt";
    int inputsCount = 8;
    int outputsCount = 1;

    // create training set from file
    DataSet dataSet = DataSet.createFromFile(trainingSetFileName, inputsCount, outputsCount, "\t", false);

    // split data into training and test set
    DataSet[] trainTestSplit = dataSet.split(0.6, 0.4);
    DataSet trainingSet = trainTestSplit[0];
    DataSet testSet = trainTestSplit[1];

    // normalize training and test set
    Normalizer norm = new MaxNormalizer(trainingSet);
    norm.normalize(trainingSet);
    norm.normalize(testSet);

    System.out.println("Creating neural network...");
    MultiLayerPerceptron neuralNet = new MultiLayerPerceptron(TransferFunctionType.TANH, inputsCount, 15, 5, outputsCount);

    neuralNet.setLearningRule(new MomentumBackpropagation());
    MomentumBackpropagation learningRule = (MomentumBackpropagation) neuralNet.getLearningRule();
    learningRule.addListener(this);

    // set learning rate and max error
    learningRule.setLearningRate(0.1);
    learningRule.setMaxError(0.03);
    System.out.println("Training network...");
    // train the network with training set
    neuralNet.learn(trainingSet);
    System.out.println("Training completed.");
    System.out.println("Testing network...");

    System.out.println("Network performance on the test set");
    evaluate(neuralNet, testSet);

    System.out.println("Saving network");
    // save neural network to file
    neuralNet.save("nn1.nnet");

    System.out.println("Done.");

    System.out.println();
    System.out.println("Network outputs for test set");
    testNeuralNetwork(neuralNet, testSet);
}