NeuralSimulatedAnnealing
org.encog.neural.networks.training.anneal

Class NeuralSimulatedAnnealing

  • All Implemented Interfaces:
    MLTrain


    public class NeuralSimulatedAnnealingextends BasicTraining
    This class implements a simulated annealing training algorithm for neural networks. It is based on the generic SimulatedAnnealing class. It is used in the same manner as any other training class that implements the Train interface. There are essentially two ways you can make use of this class. Either way, you will need a score object. The score object tells the simulated annealing algorithm how well suited a neural network is. If you would like to use simulated annealing with a training set you should make use TrainingSetScore class. This score object uses a training set to score your neural network. If you would like to be more abstract, and not use a training set, you can create your own implementation of the CalculateScore method. This class can then score the networks any way that you like.
    • Constructor Detail

      • NeuralSimulatedAnnealing

        public NeuralSimulatedAnnealing(MLEncodable network,                        CalculateScore calculateScore,                        double startTemp,                        double stopTemp,                        int cycles)
        Construct a simulated annleaing trainer for a encodable MLMethod.
        Parameters:
        network - The neural network to be trained.
        calculateScore - Used to calculate the score for a MLMethod.
        startTemp - The starting temperature.
        stopTemp - The ending temperature.
        cycles - The number of cycles in a training iteration.
    • Method Detail

      • canContinue

        public boolean canContinue()
        Returns:
        True if the training can be paused, and later continued.
      • getArray

        public double[] getArray()
        Get the network as an array of doubles.
        Returns:
        The network as an array of doubles.
      • getArrayCopy

        public double[] getArrayCopy()
        Returns:
        A copy of the annealing array.
      • getCalculateScore

        public CalculateScore getCalculateScore()
        Returns:
        The object used to calculate the score.
      • getMethod

        public MLEncodable getMethod()
        Get the current best machine learning method from the training.
        Returns:
        The best machine learningm method.
      • iteration

        public void iteration()
        Perform one iteration of simulated annealing.
      • pause

        public TrainingContinuation pause()
        Description copied from interface: MLTrain
        Pause the training to continue later.
        Returns:
        A training continuation object.
      • putArray

        public void putArray(double[] array)
        Convert an array of doubles to the current best network.
        Parameters:
        array - An array.
      • randomize

        public void randomize()
        Randomize the weights and bias values. This function does most of the work of the class. Each call to this class will randomize the data according to the current temperature. The higher the temperature the more randomness.
      • resume

        public void resume(TrainingContinuation state)
        Resume training.
        Parameters:
        state - The training continuation object to use to continue.

SCaVis 1.7 © jWork.org