Package org.apache.commons.math3.ml.neuralnet.sofm.util

Class ExponentialDecayFunction

java.lang.Object

org.apache.commons.math3.ml.neuralnet.sofm.util.ExponentialDecayFunction

public class ExponentialDecayFunction
extends Object

Exponential decay function: a e-x / b, where x is the (integer) independent variable.
Class is immutable.

Since:

3.3

Constructor Summary

Constructors

Constructor	Description
ExponentialDecayFunction(double initValue, double valueAtNumCall, long numCall)	Creates an instance.

Method Summary

Modifier and Type	Method	Description
double	value(long numCall)	Computes a e-numCall / b.

Methods inherited from class java.lang.Object

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

Constructor Details

ExponentialDecayFunction

public ExponentialDecayFunction(double initValue,
 double valueAtNumCall,
 long numCall)

Creates an instance. It will be such that

• a = initValue
• b = -numCall / ln(valueAtNumCall / initValue)

Parameters:

initValue - Initial value, i.e. value(0).

valueAtNumCall - Value of the function at numCall.

numCall - Argument for which the function returns valueAtNumCall.

Throws:

NotStrictlyPositiveException - if initValue <= 0.

NotStrictlyPositiveException - if valueAtNumCall <= 0.

NumberIsTooLargeException - if valueAtNumCall >= initValue.

NotStrictlyPositiveException - if numCall <= 0.

Method Details

value

public double value(long numCall)

Computes a e-numCall / b.

Parameters:

numCall - Current step of the training task.

Returns:

the value of the function at numCall.