Package org.encog.ml.ea.train

Examples of org.encog.ml.ea.train.EvolutionaryAlgorithm.iteration()

58
59
60
61
62
63
64
65
66
67
68
    // train the neural network
   
    final EvolutionaryAlgorithm train = NEATUtil.constructNEATTrainer(pop,score);
   
    do {
      train.iteration();
      System.out.println("Epoch #" + train.getIteration() + " Error:" + train.getError()+ ", Species:" + pop.getSpecies().size());
    } while(train.getError() > 0.01);

    NEATNetwork network = (NEATNetwork)train.getCODEC().decode(train.getBestGenome());
View Full Code Here
92
93
94
95
96
97
98
99
100
101
102
   
    // see if the population can actually be used to train
    MLDataSet trainingSet = new BasicMLDataSet(XOR.XOR_INPUT, XOR.XOR_IDEAL);   
    CalculateScore score = new TrainingSetScore(trainingSet);
    EvolutionaryAlgorithm train = NEATUtil.constructNEATTrainer(pop, score);
    train.iteration();

  }
 
  @Override
  protected void tearDown() throws Exception {
View Full Code Here
48
49
50
51
52
53
54
55
56
57
58
    // create a new random population and train it
    NEATPopulation pop = new NEATPopulation(FAKE_DATA[0].length, 1, 50);
    pop.reset();
    EvolutionaryAlgorithm training1 = NEATUtil.constructNEATTrainer(pop, score);
    training1.iteration();
    // enough training for now, backup current population to continue later
    final ByteArrayOutputStream serialized1 = new ByteArrayOutputStream();
    new PersistNEATPopulation().save(serialized1, training1.getPopulation());

    // reload initial backup and continue training
View Full Code Here
57
58
59
60
61
62
63
64
65
66
67
    // reload initial backup and continue training
    EvolutionaryAlgorithm training2 = NEATUtil.constructNEATTrainer(
      (NEATPopulation)new PersistNEATPopulation().read(new ByteArrayInputStream(serialized1.toByteArray())),
      score);
    training2.iteration();
    // enough training, backup the reloaded population to continue later
    final ByteArrayOutputStream serialized2 = new ByteArrayOutputStream();
    new PersistNEATPopulation().save(serialized2, training2.getPopulation());

    // NEATTraining.init() randomly fails with a NPE in NEATGenome.getCompatibilityScore()
View Full Code Here
66
67
68
69
70
71
72
73
74
75
76
    // NEATTraining.init() randomly fails with a NPE in NEATGenome.getCompatibilityScore()
    EvolutionaryAlgorithm training3 = NEATUtil.constructNEATTrainer(
      (NEATPopulation)new PersistNEATPopulation().read(new ByteArrayInputStream(serialized2.toByteArray())),
      score);
    training3.iteration();
    final ByteArrayOutputStream serialized3 = new ByteArrayOutputStream();
    new PersistNEATPopulation().save(serialized3, training3.getPopulation());
  }

  public void testSaveRead() throws Exception
View Full Code Here
78
79
80
81
82
83
84
85
86
87
88
    final CalculateScore score = new TrainingSetScore(new BasicMLDataSet(FAKE_DATA, FAKE_DATA));
    NEATPopulation pop = new NEATPopulation(FAKE_DATA[0].length, 1, 50);
    pop.reset();
    // create a new random population and train it
    EvolutionaryAlgorithm training1 = NEATUtil.constructNEATTrainer(pop, score);
    training1.iteration();
    // enough training for now, backup current population
    final ByteArrayOutputStream serialized1 = new ByteArrayOutputStream();
    new PersistNEATPopulation().save(serialized1, training1.getPopulation());

    final Population population2 = (Population)new PersistNEATPopulation().read(new ByteArrayInputStream(
View Full Code Here
65
66
67
68
69
70
71
72
73
74
75
    // train the neural network
   
    final EvolutionaryAlgorithm train = NEATUtil.constructNEATTrainer(pop,score);
   
    do {
      train.iteration();
    } while(train.getError() > 0.01 && train.getIteration()<10000);
    Encog.getInstance().shutdown();
    NEATNetwork network = (NEATNetwork)train.getCODEC().decode(train.getBestGenome());
   
    Assert.assertTrue(train.getError()<0.01);
View Full Code Here
86
87
88
89
90
91
92
93
94
95
96
    // train the neural network
   
    final EvolutionaryAlgorithm train = NEATUtil.constructNEATTrainer(pop,score);
   
    do {
      train.iteration();
    } while(train.getError() > 0.01);

    // test the neural network
    Encog.getInstance().shutdown();
    Assert.assertTrue(train.getError()<0.01);
View Full Code Here
TOP
Copyright © 2018 www.massapi.com. 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.