TrainInstar
org.encog.neural.cpn.training

Class TrainInstar

  • All Implemented Interfaces:
    MLTrain, LearningRate


    public class TrainInstarextends BasicTrainingimplements LearningRate
    Used for Instar training of a CPN neural network. A CPN network is a hybrid supervised/unsupervised network. The Instar training handles the unsupervised portion of the training.
    • Constructor Detail

      • TrainInstar

        public TrainInstar(CPN theNetwork,           MLDataSet theTraining,           double theLearningRate,           boolean theInitWeights)
        Construct the instar training object.
        Parameters:
        theNetwork - The network to be trained.
        theTraining - The training data.
        theLearningRate - The learning rate.
        theInitWeights - True, if the weights should be initialized from the training data. If set to true, then you must have the same number of training elements as instar neurons.
    • Method Detail

      • canContinue

        public boolean canContinue()
        Specified by:
        canContinue in interface MLTrain
        Returns:
        True if the training can be paused, and later continued.
      • getMethod

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

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

        public void resume(TrainingContinuation state)
        Resume training.
        Specified by:
        resume in interface MLTrain
        Parameters:
        state - The training continuation object to use to continue.
      • setLearningRate

        public void setLearningRate(double rate)
        Set the learning rate.
        Specified by:
        setLearningRate in interface LearningRate
        Parameters:
        rate - The new learning rate

SCaVis 1.8 © jWork.org