|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectsimbad.piconode.core.operator.Operator
simbad.piconode.core.operator.ActivationFunction
simbad.piconode.core.operator.ActivationFunctionWithDerivative
public abstract class ActivationFunctionWithDerivative
This class defines the prototype for any activation function, usually used in the context of artificial neural networks. This class embeds also a prototype for defining the derivative of the function needed by learning algorithm such as back-propagation.
Constructor Summary | |
---|---|
ActivationFunctionWithDerivative()
|
Method Summary | |
---|---|
abstract double |
applyDerivativeFunction(double __value)
|
abstract double |
applyFunction(double __value)
|
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Constructor Detail |
---|
public ActivationFunctionWithDerivative()
Method Detail |
---|
public abstract double applyFunction(double __value)
applyFunction
in class ActivationFunction
public abstract double applyDerivativeFunction(double __value)
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |