Package org.encog.ml.data.basic

Examples of org.encog.ml.data.basic.BasicMLDataSet$BasicMLIterator

54
55
56
57
58
59
60
        ideal[i][j] = input[i][j];
      }
    }

    return new BasicMLDataSet(input, ideal);
  }
View Full Code Here
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
        //Degenerate training data only provides outputs as 1 or 0 (averaging over all outputs for a given set of inputs would produce something approaching the smooth training data).
        //Smooth training data provides true values for the provided input dimensions.
        create2DSmoothTainingDataGit();

        //Create the training set and train.
        MLDataSet trainingSet = new BasicMLDataSet(INPUT, IDEAL);
        MLTrain train = new SVDTraining(network, trainingSet);

        //SVD is a single step solve
        int epoch = 1;
        do
        {
            train.iteration();
            System.out.println("Epoch #" + epoch + " Error:" + train.getError());
            epoch++;
        } while ((epoch < 1) && (train.getError() > 0.001));

        // test the neural network
        System.out.println("Neural Network Results:");

        //Create a testing array which may be to a higher resoltion than the original training data
        set2DTestingArrays(100);
        trainingSet = new BasicMLDataSet(INPUT, IDEAL);

        FileWriter outFile = new FileWriter("results.csv");
        PrintWriter out = new PrintWriter(outFile);
       
       
View Full Code Here
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
        "O   O",
        " OOO "  } };
 
  public static MLDataSet generateTraining()
  {
    MLDataSet result = new BasicMLDataSet();
    for(int i=0;i<DIGITS.length;i++)
    {     
      BasicMLData ideal = new BasicMLData(DIGITS.length);
     
      // setup input
      MLData input = image2data(DIGITS[i]);
     
      // setup ideal
      for(int j=0;j<DIGITS.length;j++)
      {
        if( j==i )
          ideal.setData(j,1);
        else
          ideal.setData(j,-1);
      }
     
      // add training element
      result.add(input,ideal);
    }
    return result;
  }
View Full Code Here
52
53
54
55
56
57
58
59
60
61
62
    network.addLayer(new BasicLayer(new ActivationSigmoid(), false,
        output[0].length));
    network.getStructure().finalizeStructure();
    network.reset();

    MLDataSet trainingSet = new BasicMLDataSet(input, output);

    // train the neural network
    MLTrain train = new Backpropagation(network, trainingSet, 0.7, 0.7);

    Stopwatch sw = new Stopwatch();
View Full Code Here
72
73
74
75
76
77
78
79
80
81
82
  public static long BenchmarkEncogFlat(double[][] input, double[][] output) {
    FlatNetwork network = new FlatNetwork(input[0].length, HIDDEN_COUNT, 0,
        output[0].length, false);
    network.randomize();
    BasicMLDataSet trainingSet = new BasicMLDataSet(input, output);

    TrainFlatNetworkBackPropagation train = new TrainFlatNetworkBackPropagation(
        network, trainingSet, 0.7, 0.7);

    double[] a = new double[2];
View Full Code Here
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
72
73
74
75
76
   * @param idealSize The ideal size, 0 for unsupervised.
   * @return A NeuralDataSet that holds the contents of the CSV file.
   */
  public static MLDataSet loadCSVTOMemory(CSVFormat format,
      String filename, boolean headers, int inputSize, int idealSize) {
    MLDataSet result = new BasicMLDataSet();
    ReadCSV csv = new ReadCSV(filename, headers, format);
    while (csv.next()) {
      MLData input = null;
      MLData ideal = null;
      int index = 0;

      input = new BasicMLData(inputSize);
      for (int i = 0; i < inputSize; i++) {
        double d = csv.getDouble(index++);
        input.setData(i, d);
      }

      if (idealSize > 0) {
        ideal = new BasicMLData(idealSize);
        for (int i = 0; i < idealSize; i++) {
          double d = csv.getDouble(index++);
          ideal.setData(i, d);
        }
      }

      MLDataPair pair = new BasicMLDataPair(input, ideal);
      result.add(pair);
    }

    return result;
  }
View Full Code Here
54
55
56
57
58
59
60
          % TemporalXOR.SEQUENCE.length];
      this.ideal[i][0] = TemporalXOR.SEQUENCE[(i + 1)
          % TemporalXOR.SEQUENCE.length];
    }

    return new BasicMLDataSet(this.input, this.ideal);
  }
View Full Code Here
43
44
45
46
47
48
49
50
51
52
53
  public static double XOR_IDEAL[][] = { { 0.0 }, { 1.0 }, { 1.0 }, { 0.0 } };

 
  public static void main(String[] args)
  {
    MLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
    BasicNetwork network = EncogUtility.simpleFeedForward(2, 4, 0, 1, false);
    ResilientPropagation train = new ResilientPropagation(network, trainingSet);
    train.addStrategy(new RequiredImprovementStrategy(5));
   
    System.out.println("Perform initial train.");
View Full Code Here
243
244
245
246
247
248
249
250
251
252
253
    // first, create the machine learning method
    MLMethodFactory methodFactory = new MLMethodFactory();   
    MLMethod method = methodFactory.create(methodName, methodArchitecture, 2, outputNeurons);
   
    // second, create the data set   
    MLDataSet dataSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
   
    // third, create the trainer
    MLTrainFactory trainFactory = new MLTrainFactory(); 
    MLTrain train = trainFactory.create(method,dataSet,trainerName,trainerArgs);       
    // reset if improve is less than 1% over 5 cycles
View Full Code Here
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
      final int idealCount, final double min, final double max) {
   
    LinearCongruentialGenerator rand =
      new LinearCongruentialGenerator(seed);
   
    final BasicMLDataSet result = new BasicMLDataSet();
    for (int i = 0; i < count; i++) {
      final MLData inputData = new BasicMLData(inputCount);

      for (int j = 0; j < inputCount; j++) {
        inputData.setData(j, rand.range(min, max));
      }

      final MLData idealData = new BasicMLData(idealCount);

      for (int j = 0; j < idealCount; j++) {
        idealData.setData(j, rand.range(min, max));
      }

      final BasicMLDataPair pair = new BasicMLDataPair(inputData,
          idealData);
      result.add(pair);

    }
    return result;
  }
View Full Code Here
TOP

Related Classes of org.encog.ml.data.basic.BasicMLDataSet$BasicMLIterator

  • com.wiieditor.neuralnetwork.NeuralNetworkWrapper
  • org.encog.app.analyst.csv.AnalystClusterCSV
  • org.encog.app.analyst.util.AnalystUtility
  • org.encog.EncogError
  • org.encog.examples.clustering.kmeans.SimpleKMeans
  • org.encog.examples.neural.activation.CustomActivation
  • org.encog.examples.neural.adaline.AdalineDigits
  • org.encog.examples.neural.benchmark.AverageBenchmark
  • org.encog.examples.neural.benchmark.BinaryVsMemory
  • org.encog.examples.neural.benchmark.FahlmanEncoder
    • 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.