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

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

46
47
48
49
50
51
52
53
54
55
56
57
58
59
    network.reset();
   
    final MLDataSet training = RandomTrainingFactory.generate(1000,50000,
        INPUT_COUNT, OUTPUT_COUNT, -1, 1);
   
    ResilientPropagation rprop = new ResilientPropagation(network,training);
    rprop.setNumThreads(thread);
    for(int i=0;i<5;i++)
    {
      rprop.iteration();
    }
    long stop = System.currentTimeMillis();
    System.out.println("Result with " + thread + " was " + (stop-start));
  }
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
    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");
View Full Code Here
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
  /**
   * {@inheritDoc}
   */
  @Override
  public final void createTrainer(final boolean singleThreaded) {
    final Propagation train = new ResilientPropagation(getNetwork(),
        getTraining(), getInitialUpdate(), getMaxStep());

    if (singleThreaded) {
      train.setNumThreads(1);
    } else {
      train.setNumThreads(0);
    }

    for (final Strategy strategy : getStrategies()) {
      train.addStrategy(strategy);
    }

    setTrain(train);
  }
View Full Code Here
42
43
44
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
    BasicNetwork network1 = NetworkUtil.createXORNetworkUntrained();
    BasicNetwork network2 = NetworkUtil.createXORNetworkUntrained();
    MLDataSet trainingData = new BasicMLDataSet(XOR.XOR_INPUT,XOR.XOR_IDEAL);
   
    // train network 1, no continue
    ResilientPropagation rprop1 = new ResilientPropagation(network1,trainingData);
    rprop1.iteration();
    rprop1.iteration();
    rprop1.iteration();
    rprop1.iteration();
   
    // train network 2, continue
    ResilientPropagation rprop2 = new ResilientPropagation(network2,trainingData);
    rprop2.iteration();
    rprop2.iteration();
    TrainingContinuation state = rprop2.pause();
    rprop2 = new ResilientPropagation(network2,trainingData);
    rprop2.resume(state);
    rprop2.iteration();
    rprop2.iteration();
   
    // verify weights are the same
    double[] weights1 = NetworkCODEC.networkToArray(network1);
    double[] weights2 = NetworkCODEC.networkToArray(network2);
   
    Assert.assertEquals(rprop1.getError(), rprop2.getError(), 0.01);
    Assert.assertEquals(weights1.length, weights2.length);
    Assert.assertArrayEquals(weights1, weights2, 0.01);
   
  }
View Full Code Here
90
91
92
93
94
95
96
97
98
99
100
101
102
    network2.setBiasActivation(-1);
    network3.setBiasActivation(0.5);
   
    MLDataSet trainingData = new BasicMLDataSet(XOR.XOR_INPUT,XOR.XOR_IDEAL);
   
    MLTrain rprop1 = new ResilientPropagation(network1, trainingData);
    MLTrain rprop2 = new ResilientPropagation(network2, trainingData);
    MLTrain rprop3 = new ResilientPropagation(network3, trainingData);

    NetworkUtil.testTraining(rprop1,0.03);
    NetworkUtil.testTraining(rprop2,0.01);
    NetworkUtil.testTraining(rprop3,0.01);
   
View Full Code Here
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
   
    BasicNetwork network = EncogUtility.simpleFeedForward(2, 5, 7, 1, true);
    Randomizer randomizer = new ConsistentRandomizer(-1, 1, 19);
    //randomizer.randomize(network);
    System.out.println(network.dumpWeights());
    MLTrain rprop = new ResilientPropagation(network, trainingData);
    int iteration = 0;
    do {
      rprop.iteration();
      System.out.println(rprop.getError());
      iteration++;
    } while( iteration<5000 && rprop.getError()>0.01);
    System.out.println(iteration);
    Assert.assertTrue(iteration<40);
  }
View Full Code Here
52
53
54
55
56
57
58
59
  public void testRPROP() throws Throwable
  {
    MLDataSet trainingData = new BasicMLDataSet(XOR.XOR_INPUT,XOR.XOR_IDEAL);
   
    BasicNetwork network = NetworkUtil.createXORNetworkUntrained();
    MLTrain rprop = new ResilientPropagation(network, trainingData);
    NetworkUtil.testTraining(rprop,0.03);
  }
View Full Code Here
40
41
42
43
44
45
46
47
48
    elmanPattern.setInputNeurons(input);
    elmanPattern.addHiddenLayer(hidden);
    elmanPattern.setOutputNeurons(ideal);
    BasicNetwork network = (BasicNetwork)elmanPattern.generate();
    MLDataSet training = RandomTrainingFactory.generate(1000, 5, network.getInputCount(), network.getOutputCount(), -1, 1);
    ResilientPropagation prop = new ResilientPropagation(network,training);
    prop.iteration();
    prop.iteration();   
  }
View Full Code Here
54
55
56
57
58
59
60
61
62
    jordanPattern.setInputNeurons(input);
    jordanPattern.addHiddenLayer(hidden);
    jordanPattern.setOutputNeurons(ideal);
    BasicNetwork network = (BasicNetwork)jordanPattern.generate();
    MLDataSet training = RandomTrainingFactory.generate(1000, 5, network.getInputCount(), network.getOutputCount(), -1, 1);
    ResilientPropagation prop = new ResilientPropagation(network,training);
    prop.iteration();
    prop.iteration();   
  }
View Full Code Here
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
  public void testLimited()
  {
    MLDataSet trainingData = new BasicMLDataSet(XOR.XOR_INPUT,XOR.XOR_IDEAL);
    BasicNetwork network = NetworkUtil.createXORNetworkUntrained();   
   
    ResilientPropagation rprop = new ResilientPropagation(network,trainingData);
    rprop.iteration();
    rprop.iteration();
    network.enableConnection(1, 0, 0, false);
    network.enableConnection(1, 1, 0, false);
   
    Assert.assertTrue(network.getStructure().isConnectionLimited());
   
    Assert.assertEquals(0.0, network.getStructure().getFlat().getWeights()[0], 0.01);
    Assert.assertEquals(0.0, network.getStructure().getFlat().getWeights()[1], 0.01);
    rprop.iteration();
    rprop.iteration();
    rprop.iteration();
    rprop.iteration();
    // these connections were removed, and should not have been "trained"
    Assert.assertEquals(0.0, network.getStructure().getFlat().getWeights()[0], 0.01);
    Assert.assertEquals(0.0, network.getStructure().getFlat().getWeights()[1], 0.01);   
    rprop.finishTraining();
  }
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.