org.encog.neural.activation
Class ActivationLinear

java.lang.Object
  org.encog.neural.activation.ActivationLinear

All Implemented Interfaces:

java.io.Serializable, ActivationFunction, EncogPersistedObject

public class ActivationLinear
extends java.lang.Object
implements ActivationFunction

ActivationLinear: The Linear layer is really not an activation function at all. The input is simply passed on, unmodified, to the output. This activation function is primarily theoretical and of little actual use. Usually an activation function that scales between 0 and 1 or -1 and 1 should be used.

See Also:

Serialized Form

Constructor Summary

ActivationLinear()

Method Summary

double	activationFunction(double d) A threshold function for a neural network.
double	derivativeFunction(double d) Some training methods require the derivative.

Methods inherited from class java.lang.Object

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

Constructor Detail

ActivationLinear

public ActivationLinear()

Method Detail

activationFunction

public double activationFunction(double d)

A threshold function for a neural network.

Specified by:

activationFunction in interface ActivationFunction

Parameters:

d - The input to the function.

Returns:

The output from the function.

derivativeFunction

public double derivativeFunction(double d)

Some training methods require the derivative.

Specified by:

derivativeFunction in interface ActivationFunction

Parameters:

d - The input.

Returns:

The output.