Package org.encog.neural.networks

Examples of org.encog.neural.networks.BasicNetwork

46
47
48
49
50
51
52
53
54
55
56
    return network;
  }
 
  public static void main(String args[])
  {
    BasicNetwork network = createNetwork();
   
    MLTrain train;
   
    if( args.length>0 && args[0].equalsIgnoreCase("anneal"))
    {
View Full Code Here
76
77
78
79
80
81
82
83
84
85
86
87
    // Graph<V, E> where V is the type of the vertices
    // and E is the type of the edges
    Graph<DrawnNeuron, DrawnConnection> g = null;
   
    if( method instanceof BasicNetwork ) {
      BasicNetwork network = (BasicNetwork)method;
      g = buildGraph(network.getStructure().getFlat());
    } else if( method instanceof NEATNetwork ) {
      NEATNetwork neat = (NEATNetwork)method;
      g = buildGraph(neat);
    }
   
View Full Code Here
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
      report.header("Context Target Size");
      report.header("Context Target Offset");
      report.header("Context Count");
      report.endRow();

      BasicNetwork network = (BasicNetwork) method;
      FlatNetwork flat = network.getStructure().getFlat();
      int layerCount = network.getLayerCount();

      for (int l = 0; l < layerCount; l++) {
        report.beginRow();
        StringBuilder str = new StringBuilder();
        str.append(Format.formatInteger(l + 1));
        if (l == 0) {
          str.append(" (Output)");
        } else if (l == network.getLayerCount() - 1) {
          str.append(" (Input)");
        }
        report.cell(str.toString());
        report.cell(Format.formatInteger(flat.getLayerCounts()[l]));
        report.cell(Format.formatInteger(flat.getLayerFeedCounts()[l]));
View Full Code Here
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
  }

  private void restructureFeedforward() {
    CreateFeedforward dialog = new CreateFeedforward(EncogWorkBench
        .getInstance().getMainWindow());
    BasicNetwork network = (BasicNetwork)method;

    ActivationFunction oldActivationOutput = network.getActivation(network
        .getLayerCount() - 1);
    dialog.setActivationFunctionOutput(oldActivationOutput);
    dialog.getInputCount().setValue(network.getInputCount());
    dialog.getOutputCount().setValue(network.getOutputCount());
    int hiddenLayerCount = network.getLayerCount() - 2;

    ActivationFunction oldActivationHidden = new ActivationTANH();
    for (int i = 0; i < hiddenLayerCount; i++) {
      int num = network.getLayerNeuronCount(i + 1);
      String str = "Hidden Layer " + (i + 1) + ": " + num + " neurons";
      dialog.getHidden().getModel().addElement(str);
    }
    dialog.setActivationFunctionHidden(oldActivationHidden);

    if (dialog.process()) {
      // decide if entire network is to be recreated
      if ((dialog.getActivationFunctionHidden() != oldActivationHidden)
          || (dialog.getActivationFunctionOutput() != oldActivationOutput)
          || dialog.getHidden().getModel().size() != (network
              .getLayerCount() - 2)) {
        FeedForwardPattern feedforward = new FeedForwardPattern();
        feedforward.setActivationFunction(dialog
            .getActivationFunctionHidden());
        feedforward.setInputNeurons(dialog.getInputCount().getValue());
        for (int i = 0; i < dialog.getHidden().getModel().size(); i++) {
          String str = (String) dialog.getHidden().getModel()
              .getElementAt(i);
          int i1 = str.indexOf(':');
          int i2 = str.indexOf("neur");
          if (i1 != -1 && i2 != -1) {
            str = str.substring(i1 + 1, i2).trim();
            int neuronCount = Integer.parseInt(str);
            feedforward.addHiddenLayer(neuronCount);
          }
        }
        feedforward.setInputNeurons(dialog.getInputCount().getValue());
        feedforward.setOutputNeurons(dialog.getOutputCount().getValue());
        BasicNetwork obj = (BasicNetwork) feedforward.generate();
      } else {
        // try to prune it
        PruneSelective prune = new PruneSelective(network);
        int newInputCount = dialog.getInputCount().getValue();
        int newOutputCount = dialog.getOutputCount().getValue();
View Full Code Here
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
  public static double XOR_IDEAL[][] = { { 0.0 }, { 1.0 }, { 1.0 }, { 0.0 } };

  public static void main(final String args[]) {

    final BasicNetwork network = new BasicNetwork();
    network.addLayer(new BasicLayer(null, true, 2));
    network.addLayer(new BasicLayer(new ActivationSigmoidPosNeg(), true, 4));
    network.addLayer(new BasicLayer(new ActivationSigmoidPosNeg(), true, 1));
    network.getStructure().finalizeStructure();
    network.reset();

    final MLDataSet trainingSet = new BasicMLDataSet(
        CustomActivation.XOR_INPUT, CustomActivation.XOR_IDEAL);

   
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
    if( output<=0 ) {
      throw new EncogError("Must have at least one output for feedforward.");
    }
   
   
    final BasicNetwork result = new BasicNetwork();
    final List<String> layers = ArchitectureParse.parseLayers(architecture);
    ActivationFunction af = new ActivationLinear();

    int questionPhase = 0;
    for (final String layerStr : layers) {
      int defaultCount;
      // determine default
      if (questionPhase == 0) {
        defaultCount = input;
      } else {
        defaultCount = output;
      }

      final ArchitectureLayer layer = ArchitectureParse.parseLayer(
          layerStr, defaultCount);
      final boolean bias = layer.isBias();

      String part = layer.getName();
      if (part != null) {
        part = part.trim();
      } else {
        part = "";
      }
     
      ActivationFunction lookup = this.factory.create(part);
     
      if (lookup!=null) {
        af = lookup;
      } else {
        if (layer.isUsedDefault()) {
          questionPhase++;
          if (questionPhase > 2) {
            throw new EncogError("Only two ?'s may be used.");
          }
        }

        if (layer.getCount() == 0) {
          throw new EncogError("Unknown architecture element: "
              + architecture + ", can't parse: " + part);
        }

        result.addLayer(new BasicLayer(af, bias,
            layer.getCount()));

      }
    }

    result.getStructure().finalizeStructure();
    result.reset();

    return result;
  }
View Full Code Here
18
19
20
21
22
23
24
25
26
27
28
  @Test
  public void testRPROP() throws Throwable
  {
    MLDataSet trainingData = XOR.createNoisyXORDataSet(10);
   
    BasicNetwork network = NetworkUtil.createXORNetworkUntrained();
   
    final FoldedDataSet folded = new FoldedDataSet(trainingData);
    final MLTrain train = new ResilientPropagation(network, folded);
    final CrossValidationKFold trainFolded = new CrossValidationKFold(train,4);
   
View Full Code Here
53
54
55
56
57
58
59
60
61
62
63
  public static void main(final String args[]) {

    final MLDataSet trainingSet = TrainingSetUtil.loadCSVTOMemory(
        CSVFormat.ENGLISH, "c:\\temp\\xor.csv", false, 2, 1);
    final BasicNetwork network = EncogUtility.simpleFeedForward(2, 4, 0, 1,
        true);

    System.out.println();
    System.out.println("Training Network");
    EncogUtility.trainToError(network, trainingSet, 0.01);
View Full Code Here
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
  public static void main(final String args[]) {
   
    Encog.getInstance().registerPlugin(new EncogOpenCLPlugin());
   
    // create a neural network, without using a factory
    BasicNetwork network = new BasicNetwork();
    network.addLayer(new BasicLayer(null,false,2));
    network.addLayer(new BasicLayer(new ActivationSigmoid(),true,3));
    network.addLayer(new BasicLayer(new ActivationSigmoid(),true,1));
    network.getStructure().finalizeStructure();
    network.reset();
    new ConsistentRandomizer(-1,1).randomize(network);

    // create training data
    MLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
    final MLTrain train = new ResilientPropagation(network, trainingSet);
View Full Code Here
27
28
29
30
31
32
33
34
35
36
37
    private BasicNetwork neuralNetwork=null;
    private MLDataSet trainingSet=null;
   
    private String filePath=null;
    public NeuralNetworkWrapper(int inputNeurons,int outputNeurons){
        neuralNetwork=new BasicNetwork();
        neuralNetwork.addLayer(new BasicLayer(null,true,inputNeurons));
  neuralNetwork.addLayer(new BasicLayer(new ActivationSigmoid(),true,ProgramConfig.NEURAL_HIDDEN_LAYER_LENGTH));
  neuralNetwork.addLayer(new BasicLayer(new ActivationSigmoid(),false,outputNeurons));
  neuralNetwork.getStructure().finalizeStructure();
  neuralNetwork.reset();
View Full Code Here
TOP

Related Classes of org.encog.neural.networks.BasicNetwork

  • com.wiieditor.neuralnetwork.NeuralNetworkWrapper
  • mechanics.NeuralNetwork
  • org.encog.engine.network.activation.ActivationFunction
  • org.encog.ensemble.ml.mlp.factory.MultiLayerPerceptronFactory
  • org.encog.examples.neural.activation.CustomActivation
  • org.encog.examples.neural.adaline.AdalineDigits
  • org.encog.examples.neural.benchmark.MultiBench
  • org.encog.examples.neural.benchmark.SimpleBenchmark
  • org.encog.examples.neural.benchmark.TestConverge
  • org.encog.examples.neural.benchmark.ThreadCount
    • 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.