The Encog Project

org.encog.neural.activation
Class ActivationGaussian

java.lang.Object
  extended by org.encog.neural.activation.BasicActivationFunction
      extended by org.encog.neural.activation.ActivationGaussian
All Implemented Interfaces:
java.io.Serializable, ActivationFunction, EncogPersistedObject

public class ActivationGaussian
extends BasicActivationFunction

An activation function based on the gaussian function.

Author:
jheaton
See Also:
Serialized Form

Constructor Summary
ActivationGaussian(double center, double peak, double width)
          Create a gaussian activation function.
 
Method Summary
 void activationFunction(double[] d)
          Implements the activation function.
 java.lang.Object clone()
           
 Persistor createPersistor()
          Create a Persistor for this activation function.
 void derivativeFunction(double[] d)
          Implements the activation function derivative.
 GaussianFunction getGausian()
           
 boolean hasDerivative()
           
 
Methods inherited from class org.encog.neural.activation.BasicActivationFunction
getDescription, getName, setDescription, setName
 
Methods inherited from class java.lang.Object
equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

ActivationGaussian

public ActivationGaussian(double center,
                          double peak,
                          double width)
Create a gaussian activation function.

Parameters:
center - The center of the curve.
peak - The peak of the curve.
width - The width of the curve.
Method Detail

activationFunction

public void activationFunction(double[] d)
Implements the activation function. The array is modified according to the activation function being used. See the class description for more specific information on this type of activation function.

Parameters:
d - The input array to the activation function.

clone

public java.lang.Object clone()
Specified by:
clone in class BasicActivationFunction
Returns:
The object cloned.

createPersistor

public Persistor createPersistor()
Create a Persistor for this activation function.

Specified by:
createPersistor in interface EncogPersistedObject
Specified by:
createPersistor in class BasicActivationFunction
Returns:
The persistor.

derivativeFunction

public void derivativeFunction(double[] d)
Implements the activation function derivative. The array is modified according derivative of the activation function being used. See the class description for more specific information on this type of activation function. Propagation training requires the derivative. Some activation functions do not support a derivative and will throw an error.

Parameters:
d - The input array to the activation function.

getGausian

public GaussianFunction getGausian()
Returns:
The gaussian funcion used.

hasDerivative

public boolean hasDerivative()
Returns:
Return true, gaussian has a derivative.

The Encog Project