Package org.apache.hama.ml.math

Examples of org.apache.hama.ml.math.DenseDoubleMatrix

129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
    ann.setCostFunction(FunctionFactory
        .createDoubleDoubleFunction("SquaredError"));
    ann.setLearningRate(0.1);
    // intentionally initialize all weights to 0.5
    DoubleMatrix[] matrices = new DenseDoubleMatrix[2];
    matrices[0] = new DenseDoubleMatrix(5, 3, 0.5);
    matrices[1] = new DenseDoubleMatrix(1, 6, 0.5);
    ann.setWeightMatrices(matrices);

    double[] arr = new double[] { 0, 1 };
    DoubleVector training = new DenseDoubleVector(arr);
    DoubleVector result = ann.getOutput(training);
    assertEquals(1, result.getDimension());
    // assertEquals(3, result.get(0), 0.000001);

    // second network
    SmallLayeredNeuralNetwork ann2 = new SmallLayeredNeuralNetwork();
    ann2.addLayer(2, false, FunctionFactory.createDoubleFunction("Sigmoid"));
    ann2.addLayer(3, false, FunctionFactory.createDoubleFunction("Sigmoid"));
    ann2.addLayer(1, true, FunctionFactory.createDoubleFunction("Sigmoid"));
    ann2.setCostFunction(FunctionFactory
        .createDoubleDoubleFunction("SquaredError"));
    ann2.setLearningRate(0.3);
    // intentionally initialize all weights to 0.5
    DoubleMatrix[] matrices2 = new DenseDoubleMatrix[2];
    matrices2[0] = new DenseDoubleMatrix(3, 3, 0.5);
    matrices2[1] = new DenseDoubleMatrix(1, 4, 0.5);
    ann2.setWeightMatrices(matrices2);

    double[] test = { 0, 0 };
    double[] result2 = { 0.807476 };

    DoubleVector vec = ann2.getOutput(new DenseDoubleVector(test));
    assertArrayEquals(result2, vec.toArray(), 0.000001);

    SmallLayeredNeuralNetwork ann3 = new SmallLayeredNeuralNetwork();
    ann3.addLayer(2, false, FunctionFactory.createDoubleFunction("Sigmoid"));
    ann3.addLayer(3, false, FunctionFactory.createDoubleFunction("Sigmoid"));
    ann3.addLayer(1, true, FunctionFactory.createDoubleFunction("Sigmoid"));
    ann3.setCostFunction(FunctionFactory
        .createDoubleDoubleFunction("SquaredError"));
    ann3.setLearningRate(0.3);
    // intentionally initialize all weights to 0.5
    DoubleMatrix[] initMatrices = new DenseDoubleMatrix[2];
    initMatrices[0] = new DenseDoubleMatrix(3, 3, 0.5);
    initMatrices[1] = new DenseDoubleMatrix(1, 4, 0.5);
    ann3.setWeightMatrices(initMatrices);

    double[] instance = { 0, 1 };
    DoubleVector output = ann3.getOutput(new DenseDoubleVector(instance));
    assertEquals(0.8315410, output.get(0), 0.000001);
View Full Code Here
128
129
130
131
132
133
134
135
136
137
138
139
      double[][] matrix23 = { // 4 by 3
      { 0.2, 0.5, 0.2 }, { 0.5, 0.1, 0.5 }, { 0.1, 0.2, 0.1 },
          { 0.1, 0.2, 0.5 } };

      DoubleMatrix[] matrices = { new DenseDoubleMatrix(matrix01),
          new DenseDoubleMatrix(matrix12), new DenseDoubleMatrix(matrix23) };
      for (DoubleMatrix mat : matrices) {
        MatrixWritable.write(mat, output);
      }
      output.close();
View Full Code Here
44
45
46
47
48
49
50
51
52
53
54
    double[][] mat = { { 1, 2, 3 }, { 4, 5, 6 }, { 7, 8, 9 } };
    double[][] mat2 = { { 10, 20 }, { 30, 40 }, { 50, 60 } };
    double[][][] mats = { mat, mat2 };

    DenseDoubleMatrix[] matrices = new DenseDoubleMatrix[] {
        new DenseDoubleMatrix(mat), new DenseDoubleMatrix(mat2) };

    SmallMLPMessage message = new SmallMLPMessage(owner, true, matrices);

    Configuration conf = new Configuration();
    String strPath = "/tmp/testSmallMLPMessage";
View Full Code Here
92
93
94
95
96
97
98
99
100
101
102
103
104
105
        { 0.7, 0.8, 0.9 } };
    double[][] prevMat2 = { { 1, 2 }, { 3, 4 }, { 5, 6 } };
    double[][][] prevMats = { prevMat, prevMat2 };

    DenseDoubleMatrix[] matrices = new DenseDoubleMatrix[] {
        new DenseDoubleMatrix(mat), new DenseDoubleMatrix(mat2) };

    DenseDoubleMatrix[] prevMatrices = new DenseDoubleMatrix[] {
        new DenseDoubleMatrix(prevMat), new DenseDoubleMatrix(prevMat2) };

    boolean terminated = false;
    SmallMLPMessage message = new SmallMLPMessage(owner, terminated, matrices,
        prevMatrices);
View Full Code Here
143
144
145
146
147
148
149
150
151
152
153
    DoubleMatrix[] weightUpdates = new DoubleMatrix[this.inMemoryModel.weightMatrixList
        .size()];
    for (int i = 0; i < weightUpdates.length; ++i) {
      int row = this.inMemoryModel.weightMatrixList.get(i).getRowCount();
      int col = this.inMemoryModel.weightMatrixList.get(i).getColumnCount();
      weightUpdates[i] = new DenseDoubleMatrix(row, col);
    }

    // continue to train
    double avgTrainingError = 0.0;
    LongWritable key = new LongWritable();
View Full Code Here
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
      int sizePrevLayer = this.layerSizeList.get(layerIdx - 1);
      // row count equals to size of current size and column count equals to
      // size of previous layer
      int row = isFinalLayer ? size : size - 1;
      int col = sizePrevLayer;
      DoubleMatrix weightMatrix = new DenseDoubleMatrix(row, col);
      // initialize weights
      final Random rnd = new Random();
      weightMatrix.applyToElements(new DoubleFunction() {
        @Override
        public double apply(double value) {
          return rnd.nextDouble() - 0.5;
        }

        @Override
        public double applyDerivative(double value) {
          throw new UnsupportedOperationException("");
        }
      });
      this.weightMatrixList.add(weightMatrix);
      this.prevWeightUpdatesList.add(new DenseDoubleMatrix(row, col));
      this.squashingFunctionList.add(squashingFunction);
    }
    return layerIdx;
  }
View Full Code Here
219
220
221
222
223
224
225
226
227
228
    this.weightMatrixList = new ArrayList<DoubleMatrix>();
    this.prevWeightUpdatesList = new ArrayList<DoubleMatrix>();
    for (int i = 0; i < numOfMatrices; ++i) {
      DoubleMatrix matrix = MatrixWritable.read(input);
      this.weightMatrixList.add(matrix);
      this.prevWeightUpdatesList.add(new DenseDoubleMatrix(
          matrix.getRowCount(), matrix.getColumnCount()));
    }

  }
View Full Code Here
397
398
399
400
401
402
403
404
405
406
407
    DoubleVector output = internalResults.get(internalResults.size() - 1);
    // initialize weight update matrices
    DenseDoubleMatrix[] weightUpdateMatrices = new DenseDoubleMatrix[this.weightMatrixList
        .size()];
    for (int m = 0; m < weightUpdateMatrices.length; ++m) {
      weightUpdateMatrices[m] = new DenseDoubleMatrix(this.weightMatrixList
          .get(m).getRowCount(), this.weightMatrixList.get(m).getColumnCount());
    }
    DoubleVector deltaVec = new DenseDoubleVector(
        this.layerSizeList.get(this.layerSizeList.size() - 1));
View Full Code Here
104
105
106
107
108
109
110
111
112
113
114
  private void initializeWeightMatrix() {
    this.weightMatrice = new DenseDoubleMatrix[this.numberOfLayers - 1];
    // each layer contains one bias neuron
    for (int i = 0; i < this.numberOfLayers - 1; ++i) {
      // add weights for bias
      this.weightMatrice[i] = new DenseDoubleMatrix(this.layerSizeArray[i] + 1,
          this.layerSizeArray[i + 1]);

      this.weightMatrice[i].applyToElements(new DoubleFunction() {

        private Random rnd = new Random();
View Full Code Here
141
142
143
144
145
146
147
148
  private void initializePrevWeightUpdateMatrix() {
    this.prevWeightUpdateMatrices = new DenseDoubleMatrix[this.numberOfLayers - 1];
    for (int i = 0; i < this.prevWeightUpdateMatrices.length; ++i) {
      int row = this.layerSizeArray[i] + 1;
      int col = this.layerSizeArray[i + 1];
      this.prevWeightUpdateMatrices[i] = new DenseDoubleMatrix(row, col);
    }
  }
View Full Code Here
TOP

Related Classes of org.apache.hama.ml.math.DenseDoubleMatrix

  • org.apache.hama.ml.ann.SmallLayeredNeuralNetwork
  • org.apache.hama.ml.ann.SmallLayeredNeuralNetworkTrainer
  • org.apache.hama.ml.ann.TestSmallLayeredNeuralNetwork
  • org.apache.hama.ml.ann.TestSmallLayeredNeuralNetworkMessage
  • org.apache.hama.ml.perception.SmallMLPTrainer
  • org.apache.hama.ml.perception.SmallMultiLayerPerceptron
  • org.apache.hama.ml.perception.TestSmallMLPMessage
  • org.apache.hama.ml.perception.TestSmallMultiLayerPerceptron
  • org.apache.hama.ml.writable.MatrixWritable
  • java.util.Random
    • 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.