Neuroph

org.neuroph.core.transfer
Class TransferFunction

java.lang.Object
  extended by org.neuroph.core.transfer.TransferFunction
All Implemented Interfaces:
java.io.Serializable
Direct Known Subclasses:
Gaussian, Linear, Ramp, Sgn, Sigmoid, Step, Tanh, Trapezoid

public abstract class TransferFunction
extends java.lang.Object
implements java.io.Serializable

The TransferFunction is abstract base class for all neuron tranfer functions.

See Also:
neuroph.core.Neuron, Serialized Form

Field Summary
private static long serialVersionUID
          The class fingerprint that is set to indicate serialization compatibility with a previous version of the class.
 
Constructor Summary
TransferFunction()
           
 
Method Summary
 double getDerivative(double net)
          Returns the first derivative of this function.
abstract  double getOutput(double net)
          Returns the ouput of this function.
 java.lang.String toString()
          Returns the class name
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait
 

Field Detail

serialVersionUID

private static final long serialVersionUID
The class fingerprint that is set to indicate serialization compatibility with a previous version of the class.

See Also:
Constant Field Values
Constructor Detail

TransferFunction

public TransferFunction()
Method Detail

getOutput

public abstract double getOutput(double net)
Returns the ouput of this function.

Parameters:
net - net input

getDerivative

public double getDerivative(double net)
Returns the first derivative of this function.

Parameters:
net - net input

toString

public java.lang.String toString()
Returns the class name

Overrides:
toString in class java.lang.Object
Returns:
class name

Neuroph