Package org.encog.neural.networks.training.propagation.resilient

Examples of org.encog.neural.networks.training.propagation.resilient.ResilientPropagation

83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
        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());
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
    network = EncogUtility.simpleFeedForward(INPUT_WINDOW, PREDICT_WINDOW*2, 0, 1, true);
    network.reset();
    graph.setNetwork(network);
   
    this.trainingData = generateTraining();
    this.train = new ResilientPropagation(this.network,this.trainingData);
    btnTrain = new JButton("Train");
    this.btnTrain.addActionListener(this);
    content.add(btnTrain,BorderLayout.SOUTH);
    graph.setError(network.calculateError(this.trainingData));
  }
View Full Code Here
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
  }
 
  public static double evaluateRPROP(BasicNetwork network,MLDataSet data)
  {

    ResilientPropagation train = new ResilientPropagation(network,data);
    train.setNumThreads(1);
    long start = System.currentTimeMillis();
    System.out.println("Training 20 Iterations with RPROP");
    for(int i=1;i<=20;i++)
    {
      train.iteration();
      System.out.println("Iteration #" + i + " Error:" + train.getError());
    }
    train.finishTraining();
    long stop = System.currentTimeMillis();
    double diff = ((double)(stop - start))/1000.0;
    System.out.println("RPROP Result:" + diff + " seconds." );
    System.out.println("Final RPROP error: " + network.calculateError(data));
    return diff;
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
  }
 
  public static double evaluateMPROP(BasicNetwork network,MLDataSet data)
  {

    ResilientPropagation train = new ResilientPropagation(network,data);
    train.setNumThreads(0);
    long start = System.currentTimeMillis();
    System.out.println("Training 20 Iterations with MPROP");
    for(int i=1;i<=20;i++)
    {
      train.iteration();
      System.out.println("Iteration #" + i + " Error:" + train.getError());
    }
    train.finishTraining();
    long stop = System.currentTimeMillis();
    double diff = ((double)(stop - start))/1000.0;
    System.out.println("MPROP Result:" + diff + " seconds." );
    System.out.println("Final MPROP error: " + network.calculateError(data));
    return diff;
View Full Code Here
121
122
123
124
125
126
127
128
129
130
131
    return network;
  }

  public void train(BasicNetwork network, MLDataSet training) {
    final FoldedDataSet folded = new FoldedDataSet(training);
    final MLTrain train = new ResilientPropagation(network, folded);
    final CrossValidationKFold trainFolded = new CrossValidationKFold(train,4);

    int epoch = 1;

    do {
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
 
  public static void main(String[] args)
  {
    MLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
    BasicNetwork network = EncogUtility.simpleFeedForward(2, 4, 0, 1, false);
    ResilientPropagation train = new ResilientPropagation(network, trainingSet);
    train.addStrategy(new RequiredImprovementStrategy(5));
   
    System.out.println("Perform initial train.");
    EncogUtility.trainToError(train,0.01);
    TrainingContinuation cont = train.pause();
    System.out.println(Arrays.toString((double[])cont.getContents().get(ResilientPropagation.LAST_GRADIENTS)));
    System.out.println(Arrays.toString((double[])cont.getContents().get(ResilientPropagation.UPDATE_VALUES)));
   
    try
    {
    cont = (TrainingContinuation)SerializeObject.load(new File("resume.ser"));
    }
    catch(Exception ex)
    {
      ex.printStackTrace();
    }
   
    System.out.println("Now trying a second train, with continue from the first.  Should stop after one iteration");
    ResilientPropagation train2 = new ResilientPropagation(network, trainingSet);
    train2.resume(cont);
    EncogUtility.trainToError(train2,0.01); 
  }
View Full Code Here
68
69
70
71
72
73
74
75
76
77
78
  public static int evaluateTrain(
      final BasicNetwork network, final MLDataSet training) {
    // train the neural network
    MLTrain train;
   
    train = new ResilientPropagation(network, training);

    final long start = System.currentTimeMillis();
    final long stop = start + (10 * MILIS);

    int iterations = 0;
View Full Code Here
264
265
266
267
268
269
270
271
272
273
274
275
        + this.outputCount);

    final double strategyError = Double.parseDouble(strStrategyError);
    final int strategyCycles = Integer.parseInt(strStrategyCycles);

    final ResilientPropagation train = new ResilientPropagation(this.network, this.training);
    train.addStrategy(new ResetStrategy(strategyError, strategyCycles));

    if (strMode.equalsIgnoreCase("gui")) {
      TrainingDialog.trainDialog(train, this.network, this.training);
    } else {
      final int minutes = Integer.parseInt(strMinutes);
View Full Code Here
50
51
52
53
54
55
56
57
58
59
60
61
62
      { 0.0, 1.0 }, { 1.0, 1.0 } };

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

  public static double evaluate(BasicNetwork network, MLDataSet training) {
    ResilientPropagation rprop = new ResilientPropagation(network, training);
    double startingError = network.calculateError(training);
    for (int i = 0; i < ITERATIONS; i++) {
      rprop.iteration();
    }
    double finalError = network.calculateError(training);
    return startingError - finalError;
  }
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
    // create training data
    MLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
   
    // train the neural network
    final ResilientPropagation train = new ResilientPropagation(network, trainingSet);

    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());
View Full Code Here
TOP

Related Classes of org.encog.neural.networks.training.propagation.resilient.ResilientPropagation

  • com.wiieditor.neuralnetwork.NeuralNetworkWrapper
  • mechanics.NeuralNetwork
  • org.encog.ensemble.training.ResilientPropagationFactory
  • org.encog.examples.neural.activation.CustomActivation
  • org.encog.examples.neural.benchmark.MultiBench
  • org.encog.examples.neural.benchmark.TestConverge
  • org.encog.examples.neural.benchmark.ThreadCount
  • org.encog.examples.neural.benchmark.WeightInitialization
  • org.encog.examples.neural.cross.CrossValidateSunspot
  • org.encog.examples.neural.gui.predict.PredictSIN
    • Copyright © 2018 www.massapicom. All rights reserved.
    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.