Package org.apache.commons.collections.primitives

Examples of org.apache.commons.collections.primitives.ArrayDoubleList

124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
      }
   }

   private int findClaster(Sample sample, int clastersCount)
   {
      DoubleList clasters = new ArrayDoubleList();

      int inputsCount = sample.getInput().size();
      for (int i = 0; i < clastersCount; ++i)
      {
         clasters.add(sample.getInput().get(sample.getInput().size() - clastersCount + i));
      }

      return JNMFMathUtils.indexOfMaxElement(clasters);
   }
View Full Code Here
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
   public DoubleList transform(DoubleList vector, VariableType type)
   {
      Validate.isTrue(inClassValue != outClassValue, "inClassValue == outClassValue");
      Validate.isTrue(vector.size() > 0, "Vector calcCountOfItems is 0");

      DoubleList result = new ArrayDoubleList();

      int closestValueIndex = -1;
      double minDisnance = Double.MAX_VALUE;
      for (int i = 0; i < vector.size(); ++i)
      {
         double distance = Math.abs(vector.get(i) - inClassValue);
         if (distance < minDisnance)
         {
            closestValueIndex = i;
            minDisnance = distance;
         }
      }

      double res = closestValueIndex + 1;

      if (classToValueTable != null)
      {
         res = classToValueTable.get(res);
      }

      result.add(res);

      return result;
   }
View Full Code Here
141
142
143
144
145
146
147
148
149
150
151
152
153
   public DoubleList getResult()
   {
      Layer last = builder.getNetwork().getLayers().getLast();

      DoubleList result = new ArrayDoubleList();
      for (Neuron neuron : last.getNeurons())
      {
         result.add(neuron.getActivation());
      }

      return result;
   }
View Full Code Here
183
184
185
186
187
188
189
190
191
192
193
194
195
196
    * @return the results of execution of neural network
    */
   public DoubleList getResult()
   {
      Layer lastLayer = layers.getLast();
      DoubleList result = new ArrayDoubleList();

      for (Neuron n : lastLayer.getNeurons())
      {
         result.add(n.getActivation());
      }

      return result;
   }
View Full Code Here
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
      int[] result = new int[getOutputNeurons().size()];

      int pCount = outputNeuronsInfo.values().iterator().next().size();
      for (int i = 0; i < pCount; ++i)
      {
         DoubleList activations = new ArrayDoubleList();
         DoubleList targetValues = new ArrayDoubleList();

         for (Neuron outputNeuron : getOutputNeurons())
         {
            NeuronStepInfo step = outputNeuronsInfo.get(outputNeuron).get(i);
            activations.add(step.activation);
            targetValues.add(step.targetValue);
         }

         int indexOfMax = JNMFMathUtils.indexOfMaxElement(activations);
         if (indexOfMax == JNMFMathUtils.indexOfMaxElement(targetValues))
         {
View Full Code Here
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
      DoubleList bestWeights = null;
      double minNextE = Double.MAX_VALUE;

      for (int i = 0; i < 100; ++i)
      {
         DoubleList weights = new ArrayDoubleList(outputsCount);
         for (int j = 0; j < outputsCount; ++j)
         {
            double w = JNMFMathUtils.reflectToInterval(rand.nextDouble(), 0, 1, -1, 1);

            weights.add(w);
         }

         double nextE = calcNextE(candidate, weights);

         if (nextE < minNextE)
View Full Code Here
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
      for (Neuron candidateNeuron : candidates)
      {
         List<NeuronStepInfo> candidateInfo = candidateNeuronsInfo.get(candidateNeuron);

         DoubleList sigmas = new ArrayDoubleList();

         for (int p = 0; p < pCount; ++p)
         {
            double sigmaP = 0;
            for (int j = 0; j < outputNeuronsCount; ++j)
            {
               List<NeuronStepInfo> outputInfo = outputNeuronsInfo.get(getOutputNeurons().get(j));

               double avE = calcAvE(outputInfo);

               NeuronStepInfo stepPInfo = outputInfo.get(p);
               IFunction deriviative = candidateNeuron.getActivationFunction().getDerivative();
               sigmaP += Math.signum(calcCj(j, candidateNeuron)) * (stepPInfo.e - avE) *
                       deriviative.calc(candidateInfo.get(p).net);
            }

            sigmas.add(sigmaP);
         }

         sigmaPValues.put(candidateNeuron, sigmas);
      }
   }
View Full Code Here
126
127
128
129
130
131
132
133
134
135
136
137
138
      signalAfterTranslationEvent();
   }

   public DoubleList getOutput()
   {
      DoubleList output = new ArrayDoubleList();
      for (Neuron neuron : getNeurons())
      {
         output.add(neuron.getActivation());
      }

      return output;
   }
View Full Code Here
74
75
76
77
78
79
80
81
82
83
84
85
86
         {
            sum[i] = sum[i] + partialResult.get(i);
         }
      }

      DoubleList result = new ArrayDoubleList();
      for (int i = 0; i < sum.length; ++i)
      {
         result.add(sum[i] / forecastPerformers.size());
      }

      return result;
   }
View Full Code Here
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
   protected void calcAllErrors()
   {
      signalNewNetworkErrorCalculdated(this.sumError / (double) learningData.size());
      if (learningData.isSplitedOnClasses())
      {
         DoubleList notGuessedPercentByClasses = new ArrayDoubleList();
         for (int i = 0; i < learningData.getOutputsCount(); ++i)
         {
            double persent =
                    (double) notGuessedClasses[i] / (double) learningData.calcCountOfItems(i);

            if (Double.isNaN(persent))
            {
               persent = 0;
            }

            notGuessedPercentByClasses.add(persent);
         }

         signalNewNotGuessedLearningDataPercentCalculated(
                 (double) totalNotGuessedClasses / (double) learningData.size(),
                 notGuessedPercentByClasses);
View Full Code Here
TOP

Related Classes of org.apache.commons.collections.primitives.ArrayDoubleList

  • com.greentea.relaxation.algorithms.art2m.Art2mAlgorithm
  • com.greentea.relaxation.algorithms.cascor.CasCorMathematics
  • com.greentea.relaxation.algorithms.pnn.PNNAlgorithm
  • com.greentea.relaxation.algorithms.radialfunc.RadialBasisFunctionDataTransformer
  • com.greentea.relaxation.algorithms.StandardAlgorithm
  • com.greentea.relaxation.jnmf.gui.components.project.network.transformation.clasterization.Art2mComponent
  • com.greentea.relaxation.jnmf.gui.components.project.network.using.ForecastReport
  • com.greentea.relaxation.jnmf.model.ForecastGroup
  • com.greentea.relaxation.jnmf.model.Layer
  • com.greentea.relaxation.jnmf.model.Network
    • 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.