JMSLTM Numerical Library 6.0

com.imsl.datamining.neural
Class HiddenLayer

java.lang.Object
  extended by com.imsl.datamining.neural.Layer
      extended by com.imsl.datamining.neural.HiddenLayer
All Implemented Interfaces:
Serializable

public class HiddenLayer
extends Layer

Hidden layer in a neural network. This is created by a factory method in Network.

See Also:
Feed Forward Class Example 1, Network.createHiddenLayer(), Serialized Form

Method Summary
 Perceptron createPerceptron()
          Creates a Perceptron in this Layer of the neural network.
 Perceptron createPerceptron(Activation activation, double bias)
          Creates a Perceptron in this Layer with a specified activation function and bias.
 Perceptron[] createPerceptrons(int n)
          Creates a number of Perceptrons in this Layer of the neural network.
 Perceptron[] createPerceptrons(int n, Activation activation, double bias)
          Creates a number of Perceptrons in this Layer with the specified bias.
 
Methods inherited from class com.imsl.datamining.neural.Layer
addNode, getIndex, getNodes
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Method Detail

createPerceptron

public Perceptron createPerceptron()
Creates a Perceptron in this Layer of the neural network. The created Perceptron uses the logistic activation function and has an initial bias value of zero.


createPerceptron

public Perceptron createPerceptron(Activation activation,
                                   double bias)
Creates a Perceptron in this Layer with a specified activation function and bias.

Parameters:
activation - The Activation object which specifies the activation function to be used.
bias - A double which specifies the initial value for the bias weight.

createPerceptrons

public Perceptron[] createPerceptrons(int n)
Creates a number of Perceptrons in this Layer of the neural network. The created Perceptrons use the logistic activation function and have an initial bias value of zero.

Parameters:
n - An int which specifies the number of Perceptrons to be created.
Returns:
An array containing the created Perceptrons.

createPerceptrons

public Perceptron[] createPerceptrons(int n,
                                      Activation activation,
                                      double bias)
Creates a number of Perceptrons in this Layer with the specified bias.

Parameters:
n - An int which specifies the number of Perceptrons to be created.
activation - The Activation object which specifies the action function to be used.
bias - A double containing the initial value to be applied as the bias values for the Perceptrons.
Returns:
An array containing the created Perceptrons.

JMSLTM Numerical Library 6.0

Copyright © 1970-2009 Visual Numerics, Inc.
Built September 1 2009.