org.encog.engine.network.activation
Class ActivationCompetitive

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

All Implemented Interfaces:

Serializable, Cloneable, ActivationFunction

public class ActivationCompetitive
extends Object
implements ActivationFunction

An activation function that only allows a specified number, usually one, of the out-bound connection to win. These connections will share in the sum of the output, whereas the other neurons will receive zero. This activation function can be useful for "winner take all" layers.

See Also:

Serialized Form

Field Summary

static int

PARAM_COMPETITIVE_MAX_WINNERS The offset to the parameter that holds the max winners.

Constructor Summary

ActivationCompetitive()
Create a competitive activation function with one winner allowed.

ActivationCompetitive(int winners)
Create a competitive activation function with the specified maximum number of winners.

Method Summary

void	activationFunction(double[] x, int start, int size) Implements the activation function.
ActivationFunction	clone()
double	derivativeFunction(double d) Implements the activation function.
int	getMaxWinners()
String	getOpenCLExpression(boolean derivative) Returns the OpenCL expression for this activation function.
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

Field Detail

PARAM_COMPETITIVE_MAX_WINNERS

public static final int PARAM_COMPETITIVE_MAX_WINNERS

The offset to the parameter that holds the max winners.

See Also:

Constant Field Values

Constructor Detail

ActivationCompetitive

public ActivationCompetitive()

Create a competitive activation function with one winner allowed.

ActivationCompetitive

public ActivationCompetitive(int winners)

Create a competitive activation function with the specified maximum number of winners.

Parameters:

winners - The maximum number of winners that this function supports.

Method Detail

activationFunction

public 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 ActivationFunction clone()

Specified by:

clone in interface ActivationFunction

Overrides:

clone in class Object

Returns:

A cloned copy of this object.

derivativeFunction

public double derivativeFunction(double d)

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:

derivativeFunction in interface ActivationFunction

Parameters:

d - The input array to the activation function.

Returns:

The derivative.

getMaxWinners

public int getMaxWinners()

Returns:

The maximum number of winners this function supports.

getParamNames

public String[] getParamNames()

Specified by:

getParamNames in interface ActivationFunction

Returns:

The names of the parameters.

getParams

public double[] getParams()

Specified by:

getParams in interface ActivationFunction

Returns:

The params for this activation function.

hasDerivative

public boolean hasDerivative()

Specified by:

hasDerivative in interface ActivationFunction

Returns:

False, indication that no derivative is available for this function.

setParam

public 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.

getOpenCLExpression

public String getOpenCLExpression(boolean derivative)

Returns the OpenCL expression for this activation function.

Specified by:

getOpenCLExpression in interface ActivationFunction

Parameters:

derivative - True if we want the derivative, false otherwise.

Returns:

The OpenCL expression for this activation function.