cc.glsn.v15.neuralnet
Class SigmoidFunction

java.lang.Object
  cc.glsn.v15.neuralnet.SigmoidFunction

All Implemented Interfaces:

NetFunction, Serializable

public class SigmoidFunction
extends Object
implements NetFunction

Implementation of the sigmoid function for neural network activation. This is a common function to use for neural networks and recommended if you don't know which one to pick. Note: the sigmoid function can only return between 0 and 1. And near the edges of that, it takes an extreme input to get that. I may be doing something majorly wrong, but I'd recommend expecting outputs in the area of 0.25 - 0.75. If you are expecting boolean outputs, I'd do 0.25 = false, 0.75 = true or something like that. If you are expecting floating point output, I'd map the things you care about to 0.25-0.75 range. This seems to work well for me, but I'm no expert in neural networks or maths.

g(x)= 1/(1+e^(-x))

g'(x) = g(x) * (1 - g(x))

See Also:

Serialized Form

Constructor Summary

SigmoidFunction()

Method Summary

double	functionG(double x) get output for input of x
double	functionGprime(double x) get derivitive of function for input x used for back propogation learning

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

SigmoidFunction

public SigmoidFunction()

Method Detail

functionG

public double functionG(double x)

Description copied from interface: NetFunction

get output for input of x

Specified by:

functionG in interface NetFunction

Parameters:

x - - input

Returns:

value - g'(x)

functionGprime

public double functionGprime(double x)

Description copied from interface: NetFunction

get derivitive of function for input x used for back propogation learning

Specified by:

functionGprime in interface NetFunction

Parameters:

x - - input

Returns:

derivitive - g'(x)