Package org.encog.ml.ea.train

Examples of org.encog.ml.ea.train.EvolutionaryAlgorithm

55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
    pop.reset();

    CalculateScore score = new TrainingSetScore(trainingSet);
    // 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());

    // test the neural network
    System.out.println("Neural Network Results:");
    EncogUtility.evaluate(network, trainingSet);
   
View Full Code Here
121
122
123
124
125
126
127
128
129
130
131
132
   
    // reload the method
    method = null;
   
    if( trainer instanceof EvolutionaryAlgorithm ) {
      EvolutionaryAlgorithm ea = (EvolutionaryAlgorithm)trainer;
      method = ea.getPopulation();
    }
   
    if( method==null ) {
      method = trainer.getMethod(); 
    }
View Full Code Here
55
56
57
58
59
60
61
62
63
64
65
    CalculateScore score = new TrainingSetScore(trainingSet);
    // train the neural network
    ActivationStep step = new ActivationStep();
    step.setCenter(0.5);

    EvolutionaryAlgorithm train = NEATUtil.constructNEATTrainer(
        score, 2, 1, 10);
    //train.setOutputActivationFunction(step);
   
    return (NEATPopulation)train.getPopulation();
  }
View Full Code Here
91
92
93
94
95
96
97
98
99
    Assert.assertEquals(0.2,pop.getSurvivalRate());
   
    // 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();

  }
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
68
69
70
71
72
73
74
    final CalculateScore score = new TrainingSetScore(new BasicMLDataSet(FAKE_DATA, FAKE_DATA));

    // 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
    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()
    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());
  }
View Full Code Here
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
  {
    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(
      serialized1.toByteArray()));
    final ByteArrayOutputStream serialized2 = new ByteArrayOutputStream();
    new PersistNEATPopulation().save(serialized2, population2);
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
    pop.reset();

    CalculateScore score = new TrainingSetScore(buffer);
    // 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);
    Assert.assertTrue(network.calculateError(buffer)<0.01);
  }
View Full Code Here
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
    pop.reset();

    CalculateScore score = new TrainingSetScore(trainingSet);
    // 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);
    NEATNetwork network = (NEATNetwork)train.getCODEC().decode(train.getBestGenome());
    Assert.assertTrue(network.calculateError(trainingSet)<0.01);
  }
View Full Code Here
49
50
51
52
53
54
55
56
57
58
59
   
    MLDataSet trainingSet = new BasicMLDataSet(XOR.XOR_INPUT,XOR.XOR_IDEAL);
    NEATPopulation pop = new NEATPopulation(2,1,100);
    pop.reset();
    CalculateScore score = new TrainingSetScore(trainingSet);
    final EvolutionaryAlgorithm train = NEATUtil.constructNEATTrainer(pop,score);
       
    NEATGenome genome1 = new NEATGenome();
    genome1.setAdjustedScore(3.0);
    NEATGenome genome2 = new NEATGenome();
    genome2.setAdjustedScore(2.0);
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
   
    MLDataSet trainingSet = new BasicMLDataSet(XOR.XOR_INPUT,XOR.XOR_IDEAL);
    NEATPopulation pop = new NEATPopulation(2,1,100);
    pop.reset();
    CalculateScore score = new TrainingSetScore(trainingSet);
    final EvolutionaryAlgorithm train = NEATUtil.constructNEATTrainer(pop,score);
       
    NEATGenome genome1 = new NEATGenome();
    genome1.setAdjustedScore(3.0);
    NEATGenome genome2 = new NEATGenome();
    genome2.setAdjustedScore(2.0);
View Full Code Here
TOP

Related Classes of org.encog.ml.ea.train.EvolutionaryAlgorithm

  • org.encog.app.analyst.commands.CmdTrain
  • org.encog.neural.networks.neat.training.species.TestSortGenomesForSpecies
  • org.encog.neural.networks.training.TestNEAT
  • org.encog.persist.TestPersistPopulation
  • org.encog.persist.TestPersistPopulationNPE
  • XORNEAT
    • 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.