Propagation
org.encog.neural.networks.training.propagation

Class Propagation

    • Constructor Detail

      • Propagation

        public Propagation(ContainsFlat network,           MLDataSet training)
        Construct a propagation object.
        Parameters:
        network - The network.
        training - The training set.
    • Method Detail

      • finishTraining

        public final void finishTraining()
        Should be called after training has completed and the iteration method will not be called any further.
        Specified by:
        finishTraining in interface MLTrain
        Overrides:
        finishTraining in class BasicTraining
      • getCurrentFlatNetwork

        public final FlatNetwork getCurrentFlatNetwork()
        Returns:
        the currentFlatNetwork
      • getFlatTraining

        public final TrainFlatNetwork getFlatTraining()
        Returns:
        the flatTraining
      • getMethod

        public final MLMethod getMethod()
        Get the current best machine learning method from the training.
        Specified by:
        getMethod in interface MLTrain
        Returns:
        The best machine learningm method.
      • getNumThreads

        public final int getNumThreads()
        Returns:
        The number of threads.
      • iteration

        public final void iteration()
        Perform one training iteration.
        Specified by:
        iteration in interface MLTrain
      • iteration

        public final void iteration(int count)
        Perform the specified number of training iterations. This can be more efficient than single training iterations. This is particularly true if you are training with a GPU.
        Specified by:
        iteration in interface MLTrain
        Overrides:
        iteration in class BasicTraining
        Parameters:
        count - The number of training iterations.
      • setFlatTraining

        public final void setFlatTraining(TrainFlatNetwork flatTraining)
        Parameters:
        flatTraining - the flatTraining to set
      • setNumThreads

        public final void setNumThreads(int numThreads)
        Set the number of threads. Specify zero to tell Encog to automatically determine the best number of threads for the processor. If OpenCL is used as the target device, then this value is not used.
        Parameters:
        numThreads - The number of threads.
      • fixFlatSpot

        public void fixFlatSpot(boolean b)
        Default is true. Call this with false to disable flat spot fix. For more info on flat spot: http://www.heatonresearch.com/wiki/Flat_Spot
        Parameters:
        b - True to fix flat spots, false otherwise.
      • setErrorFunction

        public void setErrorFunction(ErrorFunction ef)

SCaVis 2.0 © jWork.ORG