org.encog.neural.activation
Interface ActivationFunction

All Superinterfaces:

EncogPersistedObject, java.io.Serializable

All Known Implementing Classes:

ActivationLinear, ActivationSigmoid, ActivationTANH

public interface ActivationFunction
extends java.io.Serializable, EncogPersistedObject

ActivationFunction: This interface allows various activation functions to be used with the neural network. Activation functions are applied to the output from each layer of a neural network. Activation functions scale the output into the desired range. Methods are provided both to process the activation function, as well as the derivative of the function. Some training algorithms, particularly back propagation, require that it be possible to take the derivative of the activation function. Not all activation functions support derivatives. If you implement an activation function that is not derivable then an exception should be thrown inside of the derivativeFunction method implementation. Non-derivable activation functions are perfectly valid, they simply cannot be used with every training algorithm.

Method Summary

double	activationFunction(double d) A activation function for a neural network.
double	derivativeFunction(double d) Performs the derivative of the activation function function on the input.

Methods inherited from interface org.encog.neural.persist.EncogPersistedObject

createPersistor, getDescription, getName, setDescription, setName

Method Detail

activationFunction

double activationFunction(double d)

A activation function for a neural network.

Parameters:

d - The input to the function.

Returns:

The output from the function.

derivativeFunction

double derivativeFunction(double d)

Performs the derivative of the activation function function on the input.

Parameters:

d - The input.

Returns:

The output.