public class Perceptron extends Node
Perceptronnode in a neural network.
Perceptronsare created by factory methods in a
Perceptron has an activation function (g)
and a bias ().
The value of a
Perceptron is given by
where are the values of nodes
input to this Perceptron with weights .
Network training will use existing bias values for the starting values for the trainer. Upon completion of network training, the bias values are set to the values computed by the trainer.
|Modifier and Type||Method and Description|
Returns the activation function.
Returns the bias for this
Sets the activation function.
Sets the bias for this
public Activation getActivation()
Activationobject indicating the activation function.
public double getBias()
doublerepresenting the bias for this
public void setActivation(Activation activation)
Activationobject which represents the activation g to be used by this
public void setBias(double bias)
doublescalar value to which the bias is to be set. The
biashas a default value of 0.
Copyright © 1970-2015 Rogue Wave Software
Built October 13 2015.