Examples of org.encog.neural.networks.training.propagation.resilient.ResilientPropagation

Package org.encog.neural.networks.training.propagation.resilient

Examples of org.encog.neural.networks.training.propagation.resilient.ResilientPropagation

org.encog.neural.networks.training.propagation.resilient.ResilientPropagation
One problem with the backpropagation algorithm is that the magnitude of the partial derivative is usually too large or too small. Further, the learning rate is a single value for the entire neural network. The resilient propagation learning algorithm uses a special update value(similar to the learning rate) for every neuron connection. Further these update values are automatically determined, unlike the learning rate of the backpropagation algorithm. For most training situations, we suggest that the resilient propagation algorithm (this class) be used for training. There are a total of three parameters that must be provided to the resilient training algorithm. Defaults are provided for each, and in nearly all cases, these defaults are acceptable. This makes the resilient propagation algorithm one of the easiest and most efficient training algorithms available. The optional parameters are: zeroTolerance - How close to zero can a number be to be considered zero. The default is 0.00000000000000001. initialUpdate - What are the initial update values for each matrix value. The default is 0.1. maxStep - What is the largest amount that the update values can step. The default is 50. Usually you will not need to use these, and you should use the constructor that does not require them. @author jheaton

      
      if( kFold>0 ) {
        trainingData = this.wrapTrainingData(trainingData);
      }
      
      MLTrain train = new ResilientPropagation(
          (ContainsFlat) file.getObject(), trainingData,
          initialUpdate, maxStep);
      
      switch( dialog.getRpropType().getSelectedIndex() )
      {

View Full Code Here

        RPROPConst.DEFAULT_INITIAL_UPDATE);
    final double maxStep = holder.getDouble(
        MLTrainFactory.PROPERTY_MAX_STEP, false,
        RPROPConst.DEFAULT_MAX_STEP);


    return new ResilientPropagation((ContainsFlat) method, training,
        initialUpdate, maxStep);
  }

View Full Code Here

    final MLDataSet trainingSet = new BasicMLDataSet(
        CustomActivation.XOR_INPUT, CustomActivation.XOR_IDEAL);


    
    // train the neural network
    final MLTrain train = new ResilientPropagation(network, trainingSet);
    // reset if improve is less than 1% over 5 cycles
    train.addStrategy(new RequiredImprovementStrategy(5));


    EncogUtility.trainToError(train, 0.01);
    
    EncogUtility.evaluate(network, trainingSet);

View Full Code Here

    MLDataSet trainingData = XOR.createNoisyXORDataSet(10);
    
    BasicNetwork network = NetworkUtil.createXORNetworkUntrained();
    
    final FoldedDataSet folded = new FoldedDataSet(trainingData); 
    final MLTrain train = new ResilientPropagation(network, folded);
    final CrossValidationKFold trainFolded = new CrossValidationKFold(train,4);
    
    EncogUtility.trainToError(trainFolded, 0.2);
    
    XOR.verifyXOR((MLRegression)trainFolded.getMethod(), 0.2);

View Full Code Here

  
  public void jsFunction_create(JSNeuralNetwork network, JSTrainingData data)
  {
    this.network = network;
    this.data = data;
    train = new ResilientPropagation(network.getNetwork(),data.getData());
  }

View Full Code Here

    network.reset();
    new ConsistentRandomizer(-1,1).randomize(network);


    // create training data
    MLDataSet trainingSet = new BasicMLDataSet(XOR_INPUT, XOR_IDEAL);
    final MLTrain train = new ResilientPropagation(network, trainingSet);
    //
    int epoch = 1;
    do {
      train.iteration();
      System.out
          .println("Epoch #" + epoch + " Error:" + train.getError());
      epoch++;
    } while(train.getError() > 0.01 && epoch<5000);
    
    
    EncogUtility.evaluate(network, trainingSet);
  }

View Full Code Here

        if(trainingSet==null){
            trainingSet=(MLDataSet)getNeuralNetworkTrainingData(ndArray);
        }else{
            trainingSet=(MLDataSet)getNeuralNetworkTrainingData(ndArray, trainingSet);
        }
        ResilientPropagation train = new ResilientPropagation(neuralNetwork, trainingSet);
       
        EncogUtility.trainToError(train, ProgramConfig.NEURAL_NETWOR_MIN_ERROR);
    }

View Full Code Here

        if(trainingSet==null){
            trainingSet=(MLDataSet)getNeuralNetworkTrainingData(nd);
        }else{
            trainingSet=(MLDataSet)getNeuralNetworkTrainingData(nd, trainingSet);
        }
        ResilientPropagation train = new ResilientPropagation (neuralNetwork, trainingSet);
       
        
        EncogUtility.trainToError(train, ProgramConfig.NEURAL_NETWOR_MIN_ERROR);
    }

View Full Code Here

        RPROPConst.DEFAULT_INITIAL_UPDATE);
    final double maxStep = holder.getDouble(
        MLTrainFactory.PROPERTY_MAX_STEP, false,
        RPROPConst.DEFAULT_MAX_STEP);


    return new ResilientPropagation((ContainsFlat) method, training,
        initialUpdate, maxStep);
  }

View Full Code Here

   * @param minutes
   *            The number of minutes to train for.
   */
  public static void trainConsole(final BasicNetwork network,
      final MLDataSet trainingSet, final int minutes) {
    final Propagation train = new ResilientPropagation(network, trainingSet);
    train.setThreadCount(0);
    EncogUtility.trainConsole(train, network, trainingSet, minutes);
  }

View Full Code Here

0 1 2 3 4 5

TOP

Related Classes of org.encog.neural.networks.training.propagation.resilient.ResilientPropagation

com.wiieditor.neuralnetwork.NeuralNetworkWrapper

mechanics.NeuralNetwork

org.encog.ensemble.training.ResilientPropagationFactory

org.encog.examples.neural.activation.CustomActivation

org.encog.examples.neural.benchmark.MultiBench

org.encog.examples.neural.benchmark.TestConverge

org.encog.examples.neural.benchmark.ThreadCount

org.encog.examples.neural.benchmark.WeightInitialization

org.encog.examples.neural.cross.CrossValidateSunspot

org.encog.examples.neural.gui.predict.PredictSIN

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.