bodhidharma.classifiers.feedforward_neural_networks
Class HiddenNode

java.lang.Object
  extended by bodhidharma.classifiers.feedforward_neural_networks.OutputNode
      extended by bodhidharma.classifiers.feedforward_neural_networks.HiddenNode

public class HiddenNode
extends OutputNode

Objects of this class represent the hidden nodes of a neural network. OutputNodes can update themselves during learning. Adjustable learning rates and momentums are permitted.

Author:
Cory McKay

Field Summary
 
Fields inherited from class bodhidharma.classifiers.feedforward_neural_networks.OutputNode
current_value, error_signal, input_values, learning_rate, momentum, number_inputs, previous_update, weights
 
Constructor Summary
HiddenNode(double n, double alpha, int inputs)
          Instantiate the HiddenNode with the given parameters.
 
Method Summary
 void update_weights(double sum)
          Updates the weights of the node during a training iteration
 
Methods inherited from class bodhidharma.classifiers.feedforward_neural_networks.OutputNode
calculate_value, get_current_value, get_error_signal_times_weight, get_weight_values, get_weights, output_values, set_input, set_weight
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Constructor Detail

HiddenNode

public HiddenNode(double n,
                  double alpha,
                  int inputs)
Instantiate the HiddenNode with the given parameters. inputs includes the bias node, which is the last one

Method Detail

update_weights

public void update_weights(double sum)
Updates the weights of the node during a training iteration

Overrides:
update_weights in class OutputNode