net.sourceforge.cilib.neuralnetwork.generic.neuron
Interface NeuronFunction

All Superinterfaces:

Cloneable, Serializable

All Known Implementing Classes:

HyperbollicTangentOutputFunction, LinearOutputFunction, SigmoidOutputFunction, TanHOutputFunction

public interface NeuronFunction
extends Cloneable

This is the interface that a Neuron output function needs to conform to.

Method Summary

Type	computeDerivativeAtPos(Type pos)
Type	computeDerivativeUsingLastOutput(Type lastOut)
Type	computeFunction(Type in)
NeuronFunction	getClone() Create a cloned copy of the current object and return it.
double	getLowerActiveRange() Return the lowerbound for the active range of this NeuronFunction
double	getUpperActiveRange() Return the upperbound for the active range of this NeuronFunction

Method Detail

getClone

NeuronFunction getClone()

Description copied from interface: Cloneable

Create a cloned copy of the current object and return it. In general the created copy will be a deep copy of the provided instance. As a result this operation an be quite expensive if used incorrectly.

Specified by:

getClone in interface Cloneable

Returns:

An exact clone of the current object instance.

See Also:

Object.clone()

computeFunction

Type computeFunction(Type in)

computeDerivativeAtPos

Type computeDerivativeAtPos(Type pos)

computeDerivativeUsingLastOutput

Type computeDerivativeUsingLastOutput(Type lastOut)

getLowerActiveRange

double getLowerActiveRange()

Return the lowerbound for the active range of this NeuronFunction

Returns:

the lowerbound

getUpperActiveRange

double getUpperActiveRange()

Return the upperbound for the active range of this NeuronFunction

Returns:

the upperbound