Documentation of 'org.neuroph.core.transfer.Gaussian' Java class
Gaussian
org.neuroph.core.transfer

Class Gaussian

  • All Implemented Interfaces:
    java.io.Serializable


    public class Gaussian
    extends TransferFunction
    implements java.io.Serializable
     Gaussian neuron transfer function.
                 -(x^2) / (2 * sigma^2)
      f(x) =    e
     
    See Also:
    Serialized Form
    • Constructor Summary

      Constructors 
      Constructor and Description
      Gaussian()
      Creates an instance of Gaussian neuron transfer
      Gaussian(Properties properties)
      Creates an instance of Gaussian neuron transfer function with the specified properties.
    • Method Summary

      All Methods Instance Methods Concrete Methods 
      Modifier and Type Method and Description
      double getDerivative(double net)
      Returns the first derivative of this function.
      double getOutput(double totalInput)
      Returns the ouput of this function.
      double getSigma()
      Returns the sigma parametar of this function
      void setSigma(double sigma)
      Sets the sigma parametar for this function
      • Methods inherited from class java.lang.Object

        equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
    • Constructor Detail

      • Gaussian

        public Gaussian()
        Creates an instance of Gaussian neuron transfer
      • Gaussian

        public Gaussian(Properties properties)
        Creates an instance of Gaussian neuron transfer function with the specified properties.
        Parameters:
        properties - properties of the Gaussian function
    • Method Detail

      • getOutput

        public double getOutput(double totalInput)
        Description copied from class: TransferFunction
        Returns the ouput of this function.
        Specified by:
        getOutput in class TransferFunction
        Parameters:
        totalInput - total input
      • getDerivative

        public double getDerivative(double net)
        Description copied from class: TransferFunction
        Returns the first derivative of this function. Note: should this method should be abstract?
        Overrides:
        getDerivative in class TransferFunction
        Parameters:
        net - total input
      • getSigma

        public double getSigma()
        Returns the sigma parametar of this function
        Returns:
        sigma parametar of this function
      • setSigma

        public void setSigma(double sigma)
        Sets the sigma parametar for this function
        Parameters:
        sigma - value for the slope parametar

DMelt 3.0 © DataMelt by jWork.ORG

You see the box below because you did not login.