Examples of org.encog.neural.networks.BasicNetwork

org.encog.neural.networks.BasicNetwork
This class implements a neural network. This class works in conjunction the Layer classes. Layers are added to the BasicNetwork to specify the structure of the neural network. The first layer added is the input layer, the final layer added is the output layer. Any layers added between these two layers are the hidden layers. The network structure is stored in the structure member. It is important to call: network.getStructure().finalizeStructure(); Once the neural network has been completely constructed.

    }
    if (hidden2 > 0) {
      pattern.addHiddenLayer(hidden2);
    }


    final BasicNetwork network = (BasicNetwork)pattern.generate();
    network.reset();
    return network;
  }

View Full Code Here

   */
  @Override
  public void randomize(final MLMethod method) {


    if (method instanceof BasicNetwork) {
      final BasicNetwork network = (BasicNetwork) method;
      for (int i = 0; i < network.getLayerCount() - 1; i++) {
        randomize(network, i);
      }
    } else if (method instanceof MLEncodable) {
      final MLEncodable encode = (MLEncodable) method;
      final double[] encoded = new double[encode.encodedArrayLength()];

View Full Code Here

    
    if( !(method instanceof BasicNetwork) ) {
      throw new EncogError("Ngyyen Widrow only works on BasicNetwork.");
    }
    
    BasicNetwork network = (BasicNetwork)method;


    new RangeRandomizer(getMin(), getMax()).randomize(network);


    int hiddenNeurons = 0;


    for(int i=1;i<network.getLayerCount()-1;i++)
    {
      hiddenNeurons+=network.getLayerNeuronCount(i);
    }


    // can't really do much, use regular randomization
    if (hiddenNeurons < 1) {
      return;
    }


    this.inputCount = network.getInputCount();
    this.beta = 0.7 * Math.pow(hiddenNeurons, 1.0 / network.getInputCount());


    super.randomize(network);
  }

View Full Code Here


  public static double XOR_IDEAL[][] = { { 0.0 }, { 1.0 }, { 1.0 }, { 0.0 } };


  public void trainAndSave() throws IOException {
    System.out.println("Training XOR network to under 1% error rate.");
    BasicNetwork network = new BasicNetwork();
    network.addLayer(new BasicLayer(2));
    network.addLayer(new BasicLayer(2));
    network.addLayer(new BasicLayer(1));
    network.getStructure().finalizeStructure();
    network.reset();


    MLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);


    // train the neural network
    final MLTrain train = new ResilientPropagation(network, trainingSet);


    do {
      train.iteration();
    } while (train.getError() > 0.009);


    double e = network.calculateError(trainingSet);
    System.out.println("Network traiined to error: " + e);


    System.out.println("Saving network");
    SerializeObject.save(new File(FILENAME), network);
  }

View Full Code Here

  public final static String SQL_UID = "xoruser";
  public final static String SQL_PWD = "xorpassword";
  
  public static void main(final String args[]) {
    
    BasicNetwork network = new BasicNetwork();
    network.addLayer(new BasicLayer(2));
    network.addLayer(new BasicLayer(2));
    network.addLayer(new BasicLayer(1));
    network.getStructure().finalizeStructure();
    network.reset();


    MLDataSet trainingSet = new SQLNeuralDataSet(
        XORSQL.SQL,
        XORSQL.INPUT_SIZE,
        XORSQL.IDEAL_SIZE,
        XORSQL.SQL_DRIVER,
        XORSQL.SQL_URL,
        XORSQL.SQL_UID,
        XORSQL.SQL_PWD);
    
    // train the neural network
    final MLTrain train = new ResilientPropagation(network, trainingSet);
    // reset if improve is less than 1% over 5 cycles
    train.addStrategy(new RequiredImprovementStrategy(5));
    
    int epoch = 1;


    do {
      train.iteration();
      System.out
          .println("Epoch #" + epoch + " Error:" + train.getError());
      epoch++;
    } while(train.getError() > 0.01);


    // test the neural network
    System.out.println("Neural Network Results:");
    for(MLDataPair pair: trainingSet ) {
      final MLData output = network.compute(pair.getInput());
      System.out.println(pair.getInput().getData(0) + "," + pair.getInput().getData(1)
          + ", actual=" + output.getData(0) + ",ideal=" + pair.getIdeal().getData(0));
    }
  }

View Full Code Here

    SerializeObject.save(new File(FILENAME), network);
  }


  public void loadAndEvaluate() throws IOException, ClassNotFoundException {
    System.out.println("Loading network");
    BasicNetwork network = (BasicNetwork) SerializeObject.load(new File(FILENAME));
    MLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
    double e = network.calculateError(trainingSet);
    System.out
        .println("Loaded network's error is(should be same as above): "
            + e);
  }

View Full Code Here

  public static final int HIDDEN_COUNT = 60;
  public static final int OUTPUT_COUNT = 20;
  
  public static BasicNetwork generateNetwork()
  {
    final BasicNetwork network = new BasicNetwork();
    network.addLayer(new BasicLayer(MultiBench.INPUT_COUNT));
    network.addLayer(new BasicLayer(MultiBench.HIDDEN_COUNT));
    network.addLayer(new BasicLayer(MultiBench.OUTPUT_COUNT));
    network.getStructure().finalizeStructure();
    network.reset();
    return network;
  }

View Full Code Here

    return diff;
  }
  
  public static void main(String args[])
  {
    BasicNetwork network = generateNetwork();
    MLDataSet data = generateTraining();
    
    double rprop = evaluateRPROP(network,data);
    double mprop = evaluateMPROP(network,data);
    double factor = rprop/mprop;

View Full Code Here

    int outputNeurons = DIGITS.length;
    
    ADALINEPattern pattern = new ADALINEPattern();
    pattern.setInputNeurons(inputNeurons);
    pattern.setOutputNeurons(outputNeurons);
    BasicNetwork network = (BasicNetwork)pattern.generate();
    
    // train it
    MLDataSet training = generateTraining();
    MLTrain train = new TrainAdaline(network,training,0.01);
    
    int epoch = 1;
    do {
      train.iteration();
      System.out
          .println("Epoch #" + epoch + " Error:" + train.getError());
      epoch++;
    } while(train.getError() > 0.01);
    
    //
    System.out.println("Error:" + network.calculateError(training));
    
    // test it
    for(int i=0;i<DIGITS.length;i++)
    {
      int output = network.winner(image2data(DIGITS[i]));
      
      for(int j=0;j<CHAR_HEIGHT;j++)
      {
        if( j==CHAR_HEIGHT-1 )
          System.out.println(DIGITS[i][j]+" -> "+output);

View Full Code Here

  public static final int OUTPUT_COUNT = 1;
  public static final int HIDDEN_COUNT = 20;
  public static final int ITERATIONS = 10;


  public static long BenchmarkEncog(double[][] input, double[][] output) {
    BasicNetwork network = new BasicNetwork();
    network.addLayer(new BasicLayer(new ActivationSigmoid(), true,
        input[0].length));
    network.addLayer(new BasicLayer(new ActivationSigmoid(), true,
        HIDDEN_COUNT));
    network.addLayer(new BasicLayer(new ActivationSigmoid(), false,
        output[0].length));
    network.getStructure().finalizeStructure();
    network.reset();


    MLDataSet trainingSet = new BasicMLDataSet(input, output);


    // train the neural network
    MLTrain train = new Backpropagation(network, trainingSet, 0.7, 0.7);

View Full Code Here

0 1 2 3 4 5 6 7 8 9

TOP

Related Classes of org.encog.neural.networks.BasicNetwork

com.wiieditor.neuralnetwork.NeuralNetworkWrapper

mechanics.NeuralNetwork

org.encog.engine.network.activation.ActivationFunction

org.encog.ensemble.ml.mlp.factory.MultiLayerPerceptronFactory

org.encog.examples.neural.activation.CustomActivation

org.encog.examples.neural.adaline.AdalineDigits

org.encog.examples.neural.benchmark.MultiBench

org.encog.examples.neural.benchmark.SimpleBenchmark

org.encog.examples.neural.benchmark.TestConverge

org.encog.examples.neural.benchmark.ThreadCount

All source code are property of their respective owners. Java is a trademark of Sun Microsystems, Inc and owned by ORACLE Inc. Contact coftware#gmail.com.