org.encog.engine.network.activation
Class ActivationElliott

java.lang.Object
  org.encog.engine.network.activation.ActivationElliott

All Implemented Interfaces:

Serializable, Cloneable, ActivationFunction

public class ActivationElliott
extends Object
implements ActivationFunction

Computationally efficient alternative to ActivationSigmoid. Its output is in the range [0, 1], and it is derivable. It will approach the 0 and 1 more slowly than Sigmoid so it might be more suitable to classification tasks than predictions tasks. Elliott, D.L. "A better activation function for artificial neural networks", 1993 http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.46.7204&rep=rep1&type=pdf

See Also:

Serialized Form

Constructor Summary

ActivationElliott()
Construct a basic HTAN activation function, with a slope of 1.

Method Summary

void	activationFunction(double[] x, int start, int size) Implements the activation function.
ActivationFunction	clone()
double	derivativeFunction(double b, double a) Calculate the derivative.
String[]	getParamNames()
double[]	getParams()
boolean	hasDerivative()
void	setParam(int index, double value) Set one of the params for this activation function.

Methods inherited from class java.lang.Object

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

Constructor Detail

ActivationElliott

public ActivationElliott()

Construct a basic HTAN activation function, with a slope of 1.

Method Detail

activationFunction

public final void activationFunction(double[] x,
                                     int start,
                                     int size)

Implements the activation function. The array is modified according to the activation function being used. See the class description for more specific information on this type of activation function.

Specified by:

activationFunction in interface ActivationFunction

Parameters:

x - The input array to the activation function.

start - The starting index.

size - The number of values to calculate.

clone

public final ActivationFunction clone()

Specified by:

clone in interface ActivationFunction

Overrides:

clone in class Object

Returns:

The object cloned;

derivativeFunction

public final double derivativeFunction(double b,
                                       double a)

Calculate the derivative. For performance reasons two numbers are provided. First, the value "b" is simply the number that we would like to calculate the derivative of. Second, the value "a", which is the value returned by the activation function, when presented with "b". We use two values because some of the most common activation functions make use of the result of the activation function. It is bad for performance to calculate this value twice. Yet, not all derivatives are calculated this way. By providing both the value before the activation function is applied ("b"), and after the activation function is applied("a"), the class can be constructed to use whichever value will be the most efficient.

Specified by:

derivativeFunction in interface ActivationFunction

Parameters:

b - The number to calculate the derivative of, the number "before" the activation function was applied.

a - The number "after" an activation function has been applied.

Returns:

The derivative.

getParamNames

public final String[] getParamNames()

Specified by:

getParamNames in interface ActivationFunction

Returns:

The names of the parameters.

getParams

public final double[] getParams()

Specified by:

getParams in interface ActivationFunction

Returns:

The params for this activation function.

hasDerivative

public final boolean hasDerivative()

Specified by:

hasDerivative in interface ActivationFunction

Returns:

Return true, Elliott activation has a derivative.

setParam

public final void setParam(int index,
                           double value)

Set one of the params for this activation function.

Specified by:

setParam in interface ActivationFunction

Parameters:

index - The index of the param to set.

value - The value to set.