Package org.encog.neural.flat.train.prop

Examples of org.encog.neural.flat.train.prop.TrainFlatNetworkBackPropagation

74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
    FlatNetwork network = new FlatNetwork(input[0].length, HIDDEN_COUNT, 0,
        output[0].length, false);
    network.randomize();
    BasicMLDataSet trainingSet = new BasicMLDataSet(input, output);

    TrainFlatNetworkBackPropagation train = new TrainFlatNetworkBackPropagation(
        network, trainingSet, 0.7, 0.7);

    double[] a = new double[2];
    double[] b = new double[1];

    Stopwatch sw = new Stopwatch();
    sw.start();
    // run epoch of learning procedure
    for (int i = 0; i < ITERATIONS; i++) {
      train.iteration();
    }
    sw.stop();

    return sw.getElapsedMilliseconds();
  }
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
    FlatNetwork network = new FlatNetwork(input[0].length, HIDDEN_COUNT, 0,
        output[0].length, false);
    network.randomize();
    BasicMLDataSet trainingSet = new BasicMLDataSet(input, output);

    TrainFlatNetworkBackPropagation train = new TrainFlatNetworkBackPropagation(
        network, trainingSet, 0.7, 0.7);

    double[] a = new double[2];
    double[] b = new double[1];

    Stopwatch sw = new Stopwatch();
    sw.start();
    // run epoch of learning procedure
    for (int i = 0; i < ITERATIONS; i++) {
      train.iteration();
    }
    sw.stop();

    return sw.getElapsedMilliseconds();
  }
View Full Code Here
98
99
100
101
102
103
104
105
106
107
  public Backpropagation(final ContainsFlat network,
      final MLDataSet training, final double learnRate,
      final double momentum) {
    super(network, training);
    ValidateNetwork.validateMethodToData(network, training);
    final TrainFlatNetworkBackPropagation backFlat = new TrainFlatNetworkBackPropagation(
        network.getFlat(), getTraining(), learnRate, momentum);
    setFlatTraining(backFlat);

  }
View Full Code Here
172
173
174
175
176
177
178
179
180
181
   */
  @Override
  public final TrainingContinuation pause() {
    final TrainingContinuation result = new TrainingContinuation();
    result.setTrainingType(this.getClass().getSimpleName());
    final TrainFlatNetworkBackPropagation backFlat = (TrainFlatNetworkBackPropagation) getFlatTraining();
    final double[] d = backFlat.getLastDelta();
    result.set(Backpropagation.LAST_DELTA, d);
    return result;
  }
View Full Code Here
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
    FlatNetwork network = new FlatNetwork(input[0].length, HIDDEN_COUNT, 0,
        output[0].length, false);
    network.randomize();
    BasicMLDataSet trainingSet = new BasicMLDataSet(input, output);

    TrainFlatNetworkBackPropagation train = new TrainFlatNetworkBackPropagation(
        network, trainingSet, 0.7, 0.7);

    double[] a = new double[2];
    double[] b = new double[1];

    Stopwatch sw = new Stopwatch();
    sw.start();
    // run epoch of learning procedure
    for (int i = 0; i < ITERATIONS; i++) {
      train.iteration();
    }
    sw.stop();

    return sw.getElapsedMilliseconds();
  }
View Full Code Here
TOP

Related Classes of org.encog.neural.flat.train.prop.TrainFlatNetworkBackPropagation

  • org.encog.examples.neural.benchmark.AverageBenchmark
  • org.encog.examples.neural.benchmark.SimpleBenchmark
  • org.encog.neural.networks.training.propagation.back.Backpropagation
  • org.encog.plugins.opencl.example.OpenCLBenchmark
    • 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.