org.vizzini.ai.neuralnetwork
Interface IActivationFunction

All Superinterfaces:
Serializable
All Known Implementing Classes:
AbstractActivationFunction, BipolarSigmoidFunction, PassThroughFunction, SigmoidFunction, ThresholdFunction, ThresholdLinearFunction

public interface IActivationFunction
extends Serializable

Defines methods required by activation functions for a neural network.

Since:
v0.1
Version:
v0.1
Author:
Jeffrey M. Thompson

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.
 

Method Detail

getMaximum

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

Since:
v0.1

getMinimum

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

Since:
v0.1

calcDerivative

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

Since:
v0.1

calculate

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

Since:
v0.1


Copyright 2007 Vizzini.org. All Rights Reserved. 2007.12.25.03.00.02