org.neuroph.contrib
Class IACFunction

java.lang.Object
  extended by org.neuroph.core.transfer.TransferFunction
      extended by org.neuroph.contrib.IACFunction
All Implemented Interfaces:
java.io.Serializable

public class IACFunction
extends TransferFunction

Transfer function for Neuron in Interactive Activation Neural Network.

Author:
Zoran Sevarac http://www.itee.uq.edu.au/~cogs2010/cmc/chapters/IAC/index2.html#Mechanism If the activation of a unit is equal to max then the net believes the hypothesis completely. If it is equal to min then the net disbelieves the hypothesis completely. The rest corresponds to an "I don't know state". The (max - a i) or (a i - min) terms ensure that the activation remains between min and max and doesn't continue to either grow or shrink without bound [2]. The -decay (ai - rest) part of the equation forces the activation to return to the rest value in the absence of external input.
See Also:
IACNetwork, IACNeuron, Serialized Form

Constructor Summary
IACFunction()
           
 
Method Summary
 double getOutput(double netInput)
          Returns the ouput of this function.
 double getOutput(double netInput, double output)
           
 
Methods inherited from class org.neuroph.core.transfer.TransferFunction
getDerivative, toString
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait
 

Constructor Detail

IACFunction

public IACFunction()
Method Detail

getOutput

public double getOutput(double netInput,
                        double output)

getOutput

public double getOutput(double netInput)
Description copied from class: TransferFunction
Returns the ouput of this function.

Specified by:
getOutput in class TransferFunction
Parameters:
netInput - net input