Examples of org.encog.mathutil.randomize.NguyenWidrowRandomizer

org.encog.mathutil.randomize.NguyenWidrowRandomizer
Implementation of Nguyen-Widrow weight initialization. This is the default weight initialization used by Encog, as it generally provides the most trainable neural network. @author St?phan Corriveau

  public final void reset() {


    if (getLayerCount() < 3) {
      (new RangeRandomizer(-1, 1)).randomize(this);
    } else {
      (new NguyenWidrowRandomizer(-1, 1)).randomize(this);
    }
  }

View Full Code Here

  }


  public static void main(final String args[]) {


    RangeRandomizer rangeRandom = new RangeRandomizer(-1, 1);
    NguyenWidrowRandomizer nwrRandom = new NguyenWidrowRandomizer(-1, 1);
    FanInRandomizer fanRandom = new FanInRandomizer();
    GaussianRandomizer gaussianRandom = new GaussianRandomizer(0, 1);


    System.out.println("Error improvement, higher is better.");
    BasicMLDataSet training = new BasicMLDataSet(XOR_INPUT,

View Full Code Here

        network.addLayer(new BasicLayer(null,true,2));
        network.addLayer(new BasicLayer(new ActivationSigmoid(),true,3));
        network.addLayer(new BasicLayer(new ActivationSigmoid(),false,3));
        network.addLayer(new BasicLayer(null,false,1));
        network.getStructure().finalizeStructure();
        (new NguyenWidrowRandomizer(-1,1)).randomize( network );
        
        return network;
    }

View Full Code Here

    case 0: // Random
      r = new RangeRandomizer(dialog.getLow().getValue(), dialog
          .getHigh().getValue());
      break;
    case 1: // Nguyen-Widrow
      r = new NguyenWidrowRandomizer(dialog.getLow().getValue(), dialog
          .getHigh().getValue());
      break;
    case 2: // Fan in
      r = new FanInRandomizer(dialog.getLow().getValue(), dialog
          .getHigh().getValue(), false);

View Full Code Here

    if (getLayerCount() < 3) {
      useNWR = false;
    }
    
    if (useNWR) {
      return new NguyenWidrowRandomizer();
    } else {
      return new RangeRandomizer(-1,1);
    }
  }

View Full Code Here

        network.addLayer(new BasicLayer(null,true,2));
        network.addLayer(new BasicLayer(new ActivationSigmoid(),true,3));
        network.addLayer(new BasicLayer(new ActivationSigmoid(),false,3));
        network.addLayer(new BasicLayer(null,false,1));
        network.getStructure().finalizeStructure();
        (new NguyenWidrowRandomizer()).randomize( network );
        
        return network;
    }

View Full Code Here

     * the same topology as this network.
     * @param trainingSet The training set.
     */
    public NeuralPSO(BasicNetwork network, MLDataSet trainingSet)        
    {   
      this(network, new NguyenWidrowRandomizer(), new TrainingSetScore(trainingSet), 20);
    }

View Full Code Here


    final int particles = holder.getInt(
        MLTrainFactory.PROPERTY_PARTICLES, false, 20);
    
    CalculateScore score = new TrainingSetScore(training);
    Randomizer randomizer = new NguyenWidrowRandomizer();
    
    final MLTrain train = new NeuralPSO((BasicNetwork)method,randomizer,score,particles);
    
    return train;
  }

View Full Code Here

TOP

Related Classes of org.encog.mathutil.randomize.NguyenWidrowRandomizer

org.encog.EncogError

org.encog.engine.network.activation.ActivationFunction

org.encog.examples.neural.benchmark.WeightInitialization

org.encog.ml.factory.train.PSOFactory

org.encog.neural.networks.BasicNetwork

org.encog.neural.networks.NetworkUtil

org.encog.neural.networks.training.pso.NeuralPSO

org.encog.workbench.tabs.mlmethod.MLMethodTab

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.