|
|||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Object mulan.classifier.neural.model.ActivationFunction mulan.classifier.neural.model.ActivationLinear
public class ActivationLinear
Implements the linear activation function. The input is simply passed to the output. This activation function is commonly used for input units of networks, which serves as a place holders for input pattern and forwards them for processing.
Constructor Summary | |
---|---|
ActivationLinear()
|
Method Summary | |
---|---|
double |
activate(double input)
Computes an output value of the function for given input. |
double |
derivative(double input)
Computes an output value of function derivation for given input. |
double |
getMax()
Gets the maximum value the function can output. |
double |
getMin()
Gets the minimum value the function can output. |
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Constructor Detail |
---|
public ActivationLinear()
Method Detail |
---|
public double activate(double input)
ActivationFunction
activate
in class ActivationFunction
input
- the input value to the function
public double derivative(double input)
ActivationFunction
derivative
in class ActivationFunction
input
- the input value to the function
public double getMax()
ActivationFunction
getMax
in class ActivationFunction
public double getMin()
ActivationFunction
getMin
in class ActivationFunction
|
|||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |