org.vizzini.ai.neuralnetwork.function
Class SigmoidFunction

java.lang.Object
  extended by org.vizzini.ai.neuralnetwork.function.AbstractActivationFunction
      extended by org.vizzini.ai.neuralnetwork.function.SigmoidFunction
All Implemented Interfaces:
Serializable, IActivationFunction

public class SigmoidFunction
extends AbstractActivationFunction

Provides a sigmoid activation function for a neural network. This function returns a value in [0,1].

Since:
v0.1
Version:
v0.3
Author:
Jeffrey M. Thompson
See Also:
Serialized Form

Constructor Summary
SigmoidFunction()
           
 
Method Summary
 double calcDerivative(double x)
          Calculate the derivative of this function at the given input.
 double calculate(double x)
          Calculate the value of this function at the given input.
 double getMaximum()
          Return the maximum value this function can produce.
 double getMinimum()
          Return the minimum value this function can produce.
 
Methods inherited from class org.vizzini.ai.neuralnetwork.function.AbstractActivationFunction
equals, toString
 
Methods inherited from class java.lang.Object
clone, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait
 

Constructor Detail

SigmoidFunction

public SigmoidFunction()
Method Detail

calcDerivative

public double calcDerivative(double x)
Calculate the derivative of this function at the given input.

Since:
v0.1

calculate

public double calculate(double x)
Calculate the value of this function at the given input.

Since:
v0.1

getMaximum

public double getMaximum()
Return the maximum value this function can produce.

Since:
v0.1

getMinimum

public double getMinimum()
Return the minimum value this function can produce.

Since:
v0.1


Copyright 2007 Vizzini.org. All Rights Reserved. 2007.12.25.03.00.02