Package org.encog.neural

Examples of org.encog.neural.NeuralNetworkError

114
115
116
117
118
119
120
121
122
123
124
    this.height = theHeight;
    this.width = theWidth;

    for (final MLDataPair pair : this) {
      if (!(pair.getInput() instanceof ImageNeuralData)) {
        throw new NeuralNetworkError(
            "Invalid class type found in ImageNeuralDataSet, only "
                + "ImageNeuralData items are allowed.");
      }

      final ImageNeuralData input = (ImageNeuralData) pair.getInput();
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
    } else if (rbfLayer.getName().equalsIgnoreCase("InverseMultiquadric")) {
      t = RBFEnum.InverseMultiquadric;
    } else if (rbfLayer.getName().equalsIgnoreCase("MexicanHat")) {
      t = RBFEnum.MexicanHat;
    } else {
      throw new NeuralNetworkError("Unknown RBF: " + rbfLayer.getName());
    }

    final ParamsHolder holder = new ParamsHolder(rbfLayer.getParams());

    final int rbfCount = holder.getInt("C", true, 0);
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
    } else if (pnnLayer.getName().equalsIgnoreCase("r")) {
      outmodel = PNNOutputMode.Regression;
    } else if (pnnLayer.getName().equalsIgnoreCase("u")) {
      outmodel = PNNOutputMode.Unsupervised;
    } else {
      throw new NeuralNetworkError("Unknown model: "
          + pnnLayer.getName());
    }

    final ParamsHolder holder = new ParamsHolder(pnnLayer.getParams());

    final String kernelStr = holder.getString("KERNEL", false, "gaussian");
   
    if (kernelStr.equalsIgnoreCase("gaussian")) {
      kernel = PNNKernelType.Gaussian;
    } else if (kernelStr.equalsIgnoreCase("reciprocal")) {
      kernel = PNNKernelType.Reciprocal;
    } else {
      throw new NeuralNetworkError("Unknown kernel: " + kernelStr);
    }
     
    final BasicPNN result = new BasicPNN(kernel, outmodel,
        inputCount, outputCount);
View Full Code Here
129
130
131
132
133
134
135
136
137
138
   * @param input
   *            NOT USED
   * @return NOT USED
   */
  public MLData compute(final MLData input) {
    throw new NeuralNetworkError(
        "Compute on BasicNetwork cannot be used, rather call"
            + " the compute(NeuralData) method on the BAMLogic.");

  }
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
    } else if (pnnLayer.getName().equalsIgnoreCase("r")) {
      outmodel = PNNOutputMode.Regression;
    } else if (pnnLayer.getName().equalsIgnoreCase("u")) {
      outmodel = PNNOutputMode.Unsupervised;
    } else {
      throw new NeuralNetworkError("Unknown model: "
          + pnnLayer.getName());
    }

    final ParamsHolder holder = new ParamsHolder(pnnLayer.getParams());

    final String kernelStr = holder.getString("KERNEL", false, "gaussian");
   
    if (kernelStr.equalsIgnoreCase("gaussian")) {
      kernel = PNNKernelType.Gaussian;
    } else if (kernelStr.equalsIgnoreCase("reciprocal")) {
      kernel = PNNKernelType.Reciprocal;
    } else {
      throw new NeuralNetworkError("Unknown kernel: " + kernelStr);
    }
     
    final BasicPNN result = new BasicPNN(kernel, outmodel,
        inputCount, outputCount);
View Full Code Here
80
81
82
83
84
85
86
87
88
89
90
    } else if (rbfLayer.getName().equalsIgnoreCase("InverseMultiquadric")) {
      t = RBFEnum.InverseMultiquadric;
    } else if (rbfLayer.getName().equalsIgnoreCase("MexicanHat")) {
      t = RBFEnum.MexicanHat;
    } else {
      throw new NeuralNetworkError("Unknown RBF: " + rbfLayer.getName());
    }

    final ParamsHolder holder = new ParamsHolder(rbfLayer.getParams());

    final int rbfCount = holder.getInt("C", true, 0);
View Full Code Here
73
74
75
76
77
78
79
80
81
82
83
   *            The new neuron count for this layer.
   */
  public void changeNeuronCount(final int layer, final int neuronCount) {

    if (neuronCount == 0) {
      throw new NeuralNetworkError("Can't decrease to zero neurons.");
    }

    final int currentCount = this.network.getLayerNeuronCount(layer);

    // is there anything to do?
View Full Code Here
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
  private void increaseNeuronCount(final int targetLayer,
      final int neuronCount) {

    // check for errors
    if (targetLayer > this.network.getLayerCount()) {
      throw new NeuralNetworkError("Invalid layer " + targetLayer);
    }

    if (neuronCount <= 0) {
      throw new NeuralNetworkError("Invalid neuron count " + neuronCount);
    }

    final int oldNeuronCount = this.network
        .getLayerNeuronCount(targetLayer);
    final int increaseBy = neuronCount - oldNeuronCount;

    if (increaseBy <= 0) {
      throw new NeuralNetworkError(
          "New neuron count is either a decrease or no change: "
              + neuronCount);
    }

    // access the flat network
View Full Code Here
310
311
312
313
314
315
316
317
318
319
320
    // check for errors
    this.network.validateNeuron(targetLayer, neuron);

    // don't empty a layer
    if (this.network.getLayerNeuronCount(targetLayer) <= 1) {
      throw new NeuralNetworkError(
          "A layer must have at least a single neuron.  If you want to remove the entire layer you must create a new network.");
    }

    // access the flat network
    final FlatNetwork flat = this.network.getStructure().getFlat();
View Full Code Here
199
200
201
202
203
204
205
206
207
208
209
  public int classify(final MLData input) {
    final BiPolarNeuralData input2 = new BiPolarNeuralData(this.f1Count);
    final BiPolarNeuralData output = new BiPolarNeuralData(this.f2Count);

    if (input.size() != input2.size()) {
      throw new NeuralNetworkError("Input array size does not match.");
    }

    for (int i = 0; i < input2.size(); i++) {
      input2.setData(i, input.getData(i) > 0);
    }
View Full Code Here
TOP

Related Classes of org.encog.neural.NeuralNetworkError

  • org.encog.ml.factory.method.PNNFactory
  • org.encog.ml.factory.method.RBFNetworkFactory
  • org.encog.ml.svm.SVM
  • org.encog.neural.art.ART1
  • org.encog.neural.bam.BAM
  • org.encog.neural.cpn.training.TrainInstar
  • org.encog.neural.neat.NEATCODEC
  • org.encog.neural.neat.NEATNetwork
  • org.encog.neural.neat.NEATPopulation
  • org.encog.neural.neat.training.NEATGenome
    • 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.