Package org.encog.neural.neat

Examples of org.encog.neural.neat.NEATPopulation

55
56
57
58
59
60
61
62
63
64
65
66
67
          new BasicMLData(XOR.XOR_INPUT[i]),
          new BasicMLData(XOR.XOR_IDEAL[i])));
    }
    buffer.endLoad();
   
    NEATPopulation pop = new NEATPopulation(2,1,1000);
    pop.setInitialConnectionDensity(1.0);// not required, but speeds training
    pop.reset();

    CalculateScore score = new TrainingSetScore(buffer);
    // train the neural network
   
    final EvolutionaryAlgorithm train = NEATUtil.constructNEATTrainer(pop,score);
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
87
88
    Assert.assertTrue(network.calculateError(buffer)<0.01);
  }
 
  public void testNEAT() {
    MLDataSet trainingSet = new BasicMLDataSet(XOR.XOR_INPUT, XOR.XOR_IDEAL);
    NEATPopulation pop = new NEATPopulation(2,1,1000);
    pop.setInitialConnectionDensity(1.0);// not required, but speeds training
    pop.reset();

    CalculateScore score = new TrainingSetScore(trainingSet);
    // train the neural network
   
    final EvolutionaryAlgorithm train = NEATUtil.constructNEATTrainer(pop,score);
View Full Code Here
67
68
69
70
71
72
73
74
75
  public void testPersistEG()
  {
    Population pop = generate();

    EncogDirectoryPersistence.saveObject((EG_FILENAME), pop);
    NEATPopulation pop2 = (NEATPopulation)EncogDirectoryPersistence.loadObject((EG_FILENAME));
   
    validate(pop2);
  }
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
86
    validate(pop2);
  }
 
  public void testPersistSerial() throws IOException, ClassNotFoundException
  {
    NEATPopulation pop = generate();
    validate(pop);
   
    SerializeObject.save(SERIAL_FILENAME, pop);
    NEATPopulation pop2 = (NEATPopulation)SerializeObject.load(SERIAL_FILENAME);
   
    validate(pop2);
  }
View Full Code Here
45
46
47
48
49
50
51
52
53
54
55
56
  public void testNPE() throws Exception
  {
    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());
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
  }

  public void testSaveRead() throws Exception
  {
    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();
View Full Code Here
46
47
48
49
50
51
52
53
54
55
56
57
 
  @Test
  public void testSort1() {
   
    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);
View Full Code Here
73
74
75
76
77
78
79
80
81
82
83
84
 
  @Test
  public void testSort2() {
   
    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);
View Full Code Here
51
52
53
54
55
56
57
58
59
  /**
   * {@inheritDoc}
   */
  @Override
  public MLMethod decode(final Genome genome) {
    final NEATPopulation pop = (NEATPopulation) genome.getPopulation();
    final Substrate substrate = pop.getSubstrate();
    return decode(pop, substrate, genome);
  }
View Full Code Here
TOP

Related Classes of org.encog.neural.neat.NEATPopulation

  • org.encog.engine.network.activation.ActivationSteepenedSigmoid
  • org.encog.examples.neural.xor.XORNEAT
  • org.encog.ml.ea.species.BasicSpecies
  • org.encog.ml.factory.method.NEATFactory
  • org.encog.neural.hyperneat.FactorHyperNEATGenome
  • org.encog.neural.hyperneat.HyperNEATCODEC
  • org.encog.neural.neat.training.NEATGenome
  • org.encog.neural.neat.training.NEATInnovationList
  • org.encog.neural.neat.training.NEATTraining
  • org.encog.neural.neat.training.opp.NEATMutateAddNode
    • 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.