Documentation of 'org.encog.neural.flat.FlatNetwork' Java class
FlatNetwork
Skip navigation links
org.encog.neural.flat

Class FlatNetwork

  • All Implemented Interfaces:
    java.io.Serializable, java.lang.Cloneable
    Direct Known Subclasses:
    FlatNetworkRBF

    public class FlatNetwork
extends java.lang.Object
implements java.io.Serializable, java.lang.Cloneable
    Implements a flat (vector based) neural network in the Encog Engine. This is meant to be a very highly efficient feedforward, or simple recurrent, neural network. It uses a minimum of objects and is designed with one principal in mind-- SPEED. Readability, code reuse, object oriented programming are all secondary in consideration. Vector based neural networks are also very good for GPU processing. The flat network classes will make use of the GPU if you have enabled GPU processing. See the Encog class for more info.
    See Also:
    Serialized Form

    • Field Detail

      • DEFAULT_BIAS_ACTIVATION

        public static final double DEFAULT_BIAS_ACTIVATION
        The default bias activation.
        See Also:
        Constant Field Values

      • NO_BIAS_ACTIVATION

        public static final double NO_BIAS_ACTIVATION
        The value that indicates that there is no bias activation.
        See Also:
        Constant Field Values

    • Constructor Detail

      • FlatNetwork

        public FlatNetwork()
        Default constructor.

      • FlatNetwork

        public FlatNetwork(FlatLayer[] layers)
        Create a flat network from an array of layers.
        Parameters:
        layers - The layers.

      • FlatNetwork

        public FlatNetwork(FlatLayer[] layers,
                   boolean dropout)

      • FlatNetwork

        public FlatNetwork(int input,
                   int hidden1,
                   int hidden2,
                   int output,
                   boolean tanh)
        Construct a flat neural network.
        Parameters:
        input - Neurons in the input layer.
        hidden1 - Neurons in the first hidden layer. Zero for no first hidden layer.
        hidden2 - Neurons in the second hidden layer. Zero for no second hidden layer.
        output - Neurons in the output layer.
        tanh - True if this is a tanh activation, false for sigmoid.

    • Method Detail

      • calculateError

        public double calculateError(MLDataSet data)
        Calculate the error for this neural network. The error is calculated using root-mean-square(RMS).
        Parameters:
        data - The training set.
        Returns:
        The error percentage.

      • clearConnectionLimit

        public void clearConnectionLimit()
        Clear any connection limits.

      • clearContext

        public void clearContext()
        Clear any context neurons.

      • clone

        public FlatNetwork clone()
        Clone the network.
        Overrides:
        clone in class java.lang.Object
        Returns:
        A clone of the network.

      • cloneFlatNetwork

        public void cloneFlatNetwork(FlatNetwork result)
        Clone into the flat network passed in.
        Parameters:
        result - The network to copy into.

      • compute

        public void compute(double[] input,
                    double[] output)
        Calculate the output for the given input.
        Parameters:
        input - The input.
        output - Output will be placed here.

      • decodeNetwork

        public void decodeNetwork(double[] data)
        Decode the specified data into the weights of the neural network. This method performs the opposite of encodeNetwork.
        Parameters:
        data - The data to be decoded.

      • encodeNetwork

        public double[] encodeNetwork()
        Encode the neural network to an array of doubles. This includes the network weights. To read this into a neural network, use the decodeNetwork method.
        Returns:
        The encoded network.

      • getActivationFunctions

        public ActivationFunction[] getActivationFunctions()
        Returns:
        The activation functions.

      • getBeginTraining

        public int getBeginTraining()
        Returns:
        the beginTraining

      • getBiasActivation

        public double[] getBiasActivation()
        Returns:
        The bias activation.

      • getConnectionLimit

        public double getConnectionLimit()
        Returns:
        the connectionLimit

      • getContextTargetOffset

        public int[] getContextTargetOffset()
        Returns:
        The offset of the context target for each layer.

      • getContextTargetSize

        public int[] getContextTargetSize()
        Returns:
        The context target size for each layer. Zero if the layer does not feed a context layer.

      • getEncodeLength

        public int getEncodeLength()
        Returns:
        The length of the array the network would encode to.

      • getEndTraining

        public int getEndTraining()
        Returns:
        the endTraining

      • getHasContext

        public boolean getHasContext()
        Returns:
        True if this network has context.

      • getInputCount

        public int getInputCount()
        Returns:
        The number of input neurons.

      • getLayerContextCount

        public int[] getLayerContextCount()
        Returns:
        The layer context count.

      • getLayerCounts

        public int[] getLayerCounts()
        Returns:
        The number of neurons in each layer.

      • getLayerFeedCounts

        public int[] getLayerFeedCounts()
        Returns:
        The number of neurons in each layer that are fed by the previous layer.

      • getLayerIndex

        public int[] getLayerIndex()
        Returns:
        Indexes into the weights for the start of each layer.

      • getLayerOutput

        public double[] getLayerOutput()
        Returns:
        The output for each layer.

      • getNeuronCount

        public int getNeuronCount()
        Returns:
        The neuron count.

      • getOutputCount

        public int getOutputCount()
        Returns:
        The number of output neurons.

      • getWeightIndex

        public int[] getWeightIndex()
        Returns:
        The index of each layer in the weight and threshold array.

      • getWeights

        public double[] getWeights()
        Returns:
        The index of each layer in the weight and threshold array.

      • hasSameActivationFunction

        public java.lang.Class<?> hasSameActivationFunction()
        Neural networks with only one type of activation function offer certain optimization options. This method determines if only a single activation function is used.
        Returns:
        The number of the single activation function, or -1 if there are no activation functions or more than one type of activation function.

      • init

        public void init(FlatLayer[] layers,
                 boolean dropout)
        Construct a flat network.
        Parameters:
        layers - The layers of the network to create.
        dropout - Flag to enable dropout rate for each layer.

      • isLimited

        public boolean isLimited()
        Returns:
        the isLimited

      • randomize

        public void randomize()
        Perform a simple randomization of the weights of the neural network between -1 and 1.

      • randomize

        public void randomize(double hi,
                      double lo)
        Perform a simple randomization of the weights of the neural network between the specified hi and lo.
        Parameters:
        hi - The network high.
        lo - The network low.

      • setActivationFunctions

        public void setActivationFunctions(ActivationFunction[] af)
        Set the activation functions.
        Parameters:
        af - The activation functions.

      • setBeginTraining

        public void setBeginTraining(int beginTraining)
        Parameters:
        beginTraining - the beginTraining to set

      • setBiasActivation

        public void setBiasActivation(double[] biasActivation)
        Set the bias activation.
        Parameters:
        biasActivation - The bias activation.

      • setConnectionLimit

        public void setConnectionLimit(double connectionLimit)
        Parameters:
        connectionLimit - the connectionLimit to set

      • setContextTargetOffset

        public void setContextTargetOffset(int[] contextTargetOffset)
        Set the context target offset.
        Parameters:
        contextTargetOffset - The context target offset.

      • setContextTargetSize

        public void setContextTargetSize(int[] contextTargetSize)
        Set the context target size.
        Parameters:
        contextTargetSize - The context target size.

      • setEndTraining

        public void setEndTraining(int endTraining)
        Parameters:
        endTraining - the endTraining to set

      • setHasContext

        public void setHasContext(boolean hasContext)
        Set the hasContext property.
        Parameters:
        hasContext - True if the network has context.

      • setInputCount

        public void setInputCount(int inputCount)
        Set the input count.
        Parameters:
        inputCount - The input count.

      • setLayerContextCount

        public void setLayerContextCount(int[] layerContextCount)
        Set the layer context count.
        Parameters:
        layerContextCount - The layer context count.

      • setLayerCounts

        public void setLayerCounts(int[] layerCounts)
        Set the layer counts.
        Parameters:
        layerCounts - The layer counts.

      • setLayerFeedCounts

        public void setLayerFeedCounts(int[] layerFeedCounts)

      • setLayerIndex

        public void setLayerIndex(int[] i)
        Set the layer index.
        Parameters:
        i - The layer index.

      • setLayerOutput

        public void setLayerOutput(double[] layerOutput)
        Set the layer output.
        Parameters:
        layerOutput - The layer output.

      • setOutputCount

        public void setOutputCount(int outputCount)
        Set the output count.
        Parameters:
        outputCount - The output count.

      • setWeightIndex

        public void setWeightIndex(int[] weightIndex)
        Set the weight index.
        Parameters:
        weightIndex - The weight index.

      • setWeights

        public void setWeights(double[] weights)
        Set the weights.
        Parameters:
        weights - The weights.

      • getLayerSums

        public double[] getLayerSums()
        Returns:
        the layerSums

      • setLayerSums

        public void setLayerSums(double[] d)
        Set the layer sums.
        Parameters:
        d - The layer sums.

      • getLayerDropoutRates

        public double[] getLayerDropoutRates()

      • setLayerDropoutRates

        public void setLayerDropoutRates(double[] layerDropoutRates)

      • getWeight

        public double getWeight(int fromLayer,
                        int fromNeuron,
                        int toNeuron)
        Get the weight between the two layers.
        Parameters:
        fromLayer - The from layer.
        fromNeuron - The from neuron.
        toNeuron - The to neuron.
        Returns:
        The weight value.

      • validateNeuron

        public void validateNeuron(int targetLayer,
                           int neuron)
        Validate the the specified targetLayer and neuron are valid.
        Parameters:
        targetLayer - The target layer.
        neuron - The target neuron.

      • getLayerTotalNeuronCount

        public int getLayerTotalNeuronCount(int l)
        Get the total (including bias and context) neuron cont for a layer.
        Parameters:
        l - The layer.
        Returns:
        The count.

      • getLayerNeuronCount

        public int getLayerNeuronCount(int l)
        Get the neuron count.
        Parameters:
        l - The layer.
        Returns:
        The neuron count.
Skip navigation links

DMelt 3.0 © DataMelt by jWork.ORG

You see the box below because you did not login.