Examples of org.encog.neural.networks.training.propagation.manhattan.ManhattanPropagation

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

Examples of org.encog.neural.networks.training.propagation.manhattan.ManhattanPropagation

org.encog.neural.networks.training.propagation.manhattan.ManhattanPropagation
One problem that the backpropagation technique has is that the magnitude of the partial derivative may be calculated too large or too small. The Manhattan update algorithm attempts to solve this by using the partial derivative to only indicate the sign of the update to the weight matrix. The actual amount added or subtracted from the weight matrix is obtained from a simple constant. This constant must be adjusted based on the type of neural network being trained. In general, start with a higher constant and decrease it as needed. The Manhattan update algorithm can be thought of as a simplified version of the resilient algorithm. The resilient algorithm uses more complex techniques to determine the update value. @author jheaton

  public void testManhattan() throws Throwable
  {
    MLDataSet trainingData = new BasicMLDataSet(XOR.XOR_INPUT,XOR.XOR_IDEAL);
    
    BasicNetwork network = NetworkUtil.createXORNetworkUntrained();
    MLTrain bprop = new ManhattanPropagation(network, trainingData, 0.01);
    NetworkUtil.testTraining(bprop,0.01);
  }

View Full Code Here


      if( kFold>0 ) {
        trainingData = this.wrapTrainingData(trainingData);
      }
      
      MLTrain train = new ManhattanPropagation(
          (BasicNetwork) file.getObject(), trainingData, learningRate);
      
      if( kFold>0 ) {
        train = this.wrapTrainer(trainingData,train,kFold);
      }

View Full Code Here

    final ParamsHolder holder = new ParamsHolder(args);


    final double learningRate = holder.getDouble(
        MLTrainFactory.PROPERTY_LEARNING_RATE, false, 0.1);


    return new ManhattanPropagation((BasicNetwork) method, training,
        learningRate);
  }

View Full Code Here

  public void testManhattan() throws Throwable
  {
    MLDataSet trainingData = new BasicMLDataSet(XOR.XOR_INPUT,XOR.XOR_IDEAL);
    
    BasicNetwork network = NetworkUtil.createXORNetworkUntrained();
    MLTrain bprop = new ManhattanPropagation(network, trainingData, 0.01);
    NetworkUtil.testTraining(trainingData,bprop,0.01);
  }

View Full Code Here

    return this.learningRate;
  }


  @Override
  public MLTrain getTraining(MLMethod mlMethod, MLDataSet trainingData) {
    return (MLTrain) new ManhattanPropagation((BasicNetwork) mlMethod, trainingData, 0.01);
  }

View Full Code Here

    final ParamsHolder holder = new ParamsHolder(args);


    final double learningRate = holder.getDouble(
        MLTrainFactory.PROPERTY_LEARNING_RATE, false, 0.1);


    return new ManhattanPropagation((BasicNetwork) method, training,
        learningRate);
  }

View Full Code Here

TOP

Related Classes of org.encog.neural.networks.training.propagation.manhattan.ManhattanPropagation

org.encog.EncogError

org.encog.ensemble.training.ManhattanPropagationFactory

org.encog.ml.factory.train.ManhattanFactory

org.encog.neural.flat.train.prop.TrainFlatNetworkManhattan

org.encog.neural.networks.training.TestTraining

org.encog.workbench.process.TrainBasicNetwork

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.