public class Gaussian extends TransferFunction implements Serializable
Gaussian neuron transfer function. -(x^2) / (2 * sigma^2) f(x) = e
output
Constructor and Description |
---|
Gaussian()
Creates an instance of Gaussian neuron transfer
|
Gaussian(Properties properties)
Creates an instance of Gaussian neuron transfer function with the
specified properties.
|
Modifier and Type | Method and Description |
---|---|
double |
getDerivative(double net)
Returns the first derivative of this function.
|
double |
getOutput(double totalInput)
Returns the ouput of this function.
|
double |
getSigma()
Returns the sigma parametar of this function
|
void |
setSigma(double sigma)
Sets the sigma parametar for this function
|
public Gaussian()
public Gaussian(Properties properties)
properties
- properties of the Gaussian functionpublic double getOutput(double totalInput)
TransferFunction
getOutput
in class TransferFunction
totalInput
- total inputpublic double getDerivative(double net)
TransferFunction
getDerivative
in class TransferFunction
net
- total inputpublic double getSigma()
public void setSigma(double sigma)
sigma
- value for the slope parametarCopyright © 2019 Neuroph Project. All rights reserved.