Package com.github.neuralnetworks.util

Examples of com.github.neuralnetworks.util.Matrix

103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
    @Test
    public void testRBMLayerCalculator1() {
  RBM rbm = NNFactory.rbm(2, 2, false);
  rbm.setLayerCalculator(NNFactory.rbmSigmoidSigmoid(rbm));

  Matrix cg1 = rbm.getMainConnections().getConnectionGraph();
  cg1.set(0.1f, 0, 0);
  cg1.set(0.8f, 0, 1);
  cg1.set(0.4f, 1, 0);
  cg1.set(0.6f, 1, 1);

  RBMLayerCalculator lc = (RBMLayerCalculator) rbm.getLayerCalculator();

  Matrix visible = new Matrix(new float[] { 0.35f, 0.9f }, 1);
  Matrix hidden = new Matrix(2, 1);
  lc.calculateHiddenLayer(rbm, visible, hidden);

  assertEquals(0.68, hidden.get(0, 0), 0.01);
  assertEquals(0.6637, hidden.get(1, 0), 0.01);
    }
View Full Code Here
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
    @Test
    public void testRBMLayerCalculator2() {
  RBM rbm = NNFactory.rbm(2, 2, false);
  rbm.setLayerCalculator(NNFactory.rbmSigmoidSigmoid(rbm));

  Matrix cg1 = rbm.getMainConnections().getConnectionGraph();
  cg1.set(0.1f, 0, 0);
  cg1.set(0.8f, 1, 0);
  cg1.set(0.4f, 0, 1);
  cg1.set(0.6f, 1, 1);

  RBMLayerCalculator lc = (RBMLayerCalculator) rbm.getLayerCalculator();

  Matrix visible = new Matrix(2, 1);
  Matrix hidden = new Matrix(new float[] { 0.35f, 0.9f }, 1);

  lc.calculateVisibleLayer(rbm, visible, hidden);

  assertEquals(0.68, visible.get(0, 0), 0.01);
  assertEquals(0.6637, visible.get(1, 0), 0.01);
View Full Code Here
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
    @Test
    public void testRBMLayerCalculator3() {
  RBM rbm = NNFactory.rbm(3, 2, true);
  rbm.setLayerCalculator(NNFactory.rbmSigmoidSigmoid(rbm));

  Matrix cg1 = rbm.getMainConnections().getConnectionGraph();
  cg1.set(0.2f, 0, 0);
  cg1.set(0.4f, 0, 1);
  cg1.set(-0.5f, 0, 2);
  cg1.set(-0.3f, 1, 0);
  cg1.set(0.1f, 1, 1);
  cg1.set(0.2f, 1, 2);

  Matrix cgb1 = rbm.getHiddenBiasConnections().getConnectionGraph();
  cgb1.set(-0.4f, 0, 0);
  cgb1.set(0.2f, 1, 0);

  RBMLayerCalculator lc = (RBMLayerCalculator) rbm.getLayerCalculator();
  Matrix visible = new Matrix(new float[] { 1f, 0f, 1f }, 1);
  Matrix hidden = new Matrix(2, 1);
  lc.calculateHiddenLayer(rbm, visible, hidden);

  assertEquals(0.332, hidden.get(0, 0), 0.001);
  assertEquals(0.525, hidden.get(1, 0), 0.001);
    }
View Full Code Here
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
    @Test
    public void testRBMLayerCalculator4() {
  RBM rbm = NNFactory.rbm(2, 3, true);
  rbm.setLayerCalculator(NNFactory.rbmSigmoidSigmoid(rbm));

  Matrix cg1 = rbm.getMainConnections().getConnectionGraph();
  cg1.set(0.2f, 0, 0);
  cg1.set(0.4f, 1, 0);
  cg1.set(-0.5f, 2, 0);
  cg1.set(-0.3f, 0, 1);
  cg1.set(0.1f, 1, 1);
  cg1.set(0.2f, 2, 1);

  Matrix cgb1 = rbm.getVisibleBiasConnections().getConnectionGraph();
  cgb1.set(-0.4f, 0, 0);
  cgb1.set(0.2f, 1, 0);

  RBMLayerCalculator lc = (RBMLayerCalculator) rbm.getLayerCalculator();
  Matrix hidden = new Matrix(new float[] { 1f, 0f, 1f }, 1);
  Matrix visible = new Matrix(2, 1);
  lc.calculateVisibleLayer(rbm, visible, hidden);

  assertEquals(0.332, visible.get(0, 0), 0.001);
  assertEquals(0.525, visible.get(1, 0), 0.001);
    }
View Full Code Here
25
26
27
28
29
30
31
32
33
34
35
  results = new ValuesProvider();
  intermediateResults = new ValuesProvider();
    }

    public void gibbsSampling(RBM rbm, Matrix posPhaseVisible, Matrix posPhaseHidden, Matrix negPhaseVisible, Matrix negPhaseHidden, int samplingCount, boolean resetNetwork, boolean useIntermediateResults) {
  Matrix hidden, visible;
  calculateHiddenLayer(rbm, posPhaseVisible, posPhaseHidden);

  if (resetNetwork) {
      System.arraycopy(posPhaseHidden.getElements(), 0, negPhaseHidden.getElements(), 0, negPhaseHidden.getElements().length);
  }
View Full Code Here
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
  super.calculate(rbm, hiddenLayer, calculatedLayers, results);
    }

    private Matrix getLayerResult(Layer layer, Matrix realResult, boolean useIntermediateResults) {
  Matrix result = realResult;
  if (useIntermediateResults) {
      intermediateResults.setColumns(realResult.getColumns());
      result = intermediateResults.getValues(layer, realResult.getRows());
      if (result == null) {
    intermediateResults.addValues(layer, result = new Matrix(realResult));
      }

      System.arraycopy(realResult.getElements(), 0, result.getElements(), 0, result.getElements().length);
  }

  return result;
    }
View Full Code Here
59
60
61
62
63
64
65
66
67
68
69
70
71
  if (!values.containsKey(targetLayer)) {
      values.put(targetLayer, new HashSet<Matrix>());
  }

  Set<Matrix> set = values.get(targetLayer);
  Matrix result = set.stream().filter(m -> m.getRows() == rows && m.getColumns() == getColumns()).findFirst().orElse(null);

  if (result == null) {
      set.add(result = new Matrix(rows, getColumns()));
  }

  return result;
    }
View Full Code Here
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
  this.weightsInitialStep = new int[series];
  this.weightsStep = new int[series];

  int totalInputSize = 0, totalWeightSize = 0, i = 0;
  for (java.util.Map.Entry<GraphConnections, Integer> e : inputConnections.entrySet()) {
      Matrix cg = e.getKey().getConnectionGraph();

      inputStartPositions[i] = totalInputSize;
      totalInputSize += e.getValue();
      weightStartPositions[i] = totalWeightSize;
      totalWeightSize += e.getKey().getConnectionGraph().getElements().length;

      // depending on the direction of the calculation
      if (e.getKey().getOutputLayer() == targetLayer) {
    weightsDimension[i] = cg.getColumns();
    weightsInitialStep[i] = cg.getColumns();
    weightsStep[i] = 1;
      } else {
    weightsDimension[i] = cg.getRows();
    weightsInitialStep[i] = 1;
    weightsStep[i] = cg.getColumns();
      }

      i++;
  }
View Full Code Here
16
17
18
19
20
21
22
    public FullyConnected(Layer inputLayer, Layer outputLayer, int inputUnitCount, int outputUnitCount) {
  super(inputLayer, outputLayer);

  // connection graph is initialized depending on the size of the input/output layers
  connectionGraph = new Matrix(new float[inputUnitCount * outputUnitCount], inputUnitCount);
    }
View Full Code Here
53
54
55
56
57
58
59
60
61
62
  }

  public void setInputOutput(Matrix inputOutput) {
      this.input = inputOutput;
      if (target == null || target.getElements().length != input.getElements().length) {
    target = new Matrix(input.getRows(), input.getColumns());
      }

      System.arraycopy(input.getElements(), 0, target.getElements(), 0, target.getElements().length);
  }
View Full Code Here
TOP

Related Classes of com.github.neuralnetworks.util.Matrix

  • com.github.neuralnetworks.architecture.FullyConnected
  • com.github.neuralnetworks.calculation.neuronfunctions.AparapiWeightedSum
  • com.github.neuralnetworks.calculation.RBMLayerCalculator
  • com.github.neuralnetworks.calculation.ValuesProvider
  • com.github.neuralnetworks.samples.iris.IrisInputProvider
  • com.github.neuralnetworks.samples.iris.IrisTargetMultiNeuronOutputConverter
  • com.github.neuralnetworks.samples.mnist.MnistInputProvider
  • com.github.neuralnetworks.samples.mnist.MnistTargetMultiNeuronOutputConverter
  • com.github.neuralnetworks.samples.mnist.MnistTargetSingleNeuronOutputConverter
  • com.github.neuralnetworks.samples.xor.XorInputProvider
    • 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.