public class ManhattanPropagationextends Propagationimplements LearningRateOne 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.
Constructors Constructor and Description
ManhattanPropagation(ContainsFlat network, MLDataSet training, double learnRate)Construct a Manhattan propagation training object.
Methods Modifier and Type Method and Description
canContinue()This training type does not support training continue.
pause()This training type does not support training continue.
resume(TrainingContinuation state)This training type does not support training continue.
setLearningRate(double rate)Set the learning rate.
Methods inherited from class org.encog.neural.networks.training.propagation.Propagation
finishTraining, fixFlatSpot, getCurrentFlatNetwork, getFlatTraining, getMethod, getNumThreads, iteration, iteration, setErrorFunction, setFlatTraining, setNumThreads
Methods inherited from class org.encog.ml.train.BasicTraining
addStrategy, getError, getImplementationType, getIteration, getStrategies, getTraining, isTrainingDone, postIteration, preIteration, setError, setIteration, setTraining
Methods inherited from class java.lang.Object
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
public final double getLearningRate()
public final void setLearningRate(double rate)Set the learning rate.
public final boolean canContinue()This training type does not support training continue.
public final TrainingContinuation pause()This training type does not support training continue.
SCaVis 2.1 © jWork.ORG