NearNeural

Class UnweightedBackPropagationMethod

java.lang.Object

NearNeural.UnweightedBackPropagationMethod

All Implemented Interfaces:

BackPropagationMethod

Direct Known Subclasses:

ThreadedUnweightedBackPropagationMethod

public class UnweightedBackPropagationMethod
extends java.lang.Object
implements BackPropagationMethod

Backpropagates a layer without any kind of weighting to avoid local minima of error.

Version:

0.3

Author:

Stephen Wattam

Field Summary

Fields

Modifier and Type	Field and Description
protected double	learningRate The multiplier for error gradient descent.

Constructor Summary

Constructors

Constructor and Description
UnweightedBackPropagationMethod(double p_learningRate) Creates a new backpropagation object with the given learning rate.

Method Summary

Methods

Modifier and Type	Method and Description
void	backPropagateHidden(NeuronLayer downstream, ReceptiveNeuron[] neurons) Back propagates a hidden layer relative to the layer immediately following it.
double	backPropagateOutputs(double[] desirable, ReceptiveNeuron[] neurons) This function back-propogates output nodes.
double	getLearningRate() Returns the current learning rate.
void	setLearningRate(double p_learningRate) Sets the learning rate of this backpropagation method.

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

learningRate

protected double learningRate

The multiplier for error gradient descent.

Constructor Detail

UnweightedBackPropagationMethod

public UnweightedBackPropagationMethod(double p_learningRate)

Creates a new backpropagation object with the given learning rate.

Parameters:

p_learningRate - The learning rate, normally arouund 0.02 or below

Method Detail

setLearningRate

public void setLearningRate(double p_learningRate)

Sets the learning rate of this backpropagation method. This is a very useful method of increasing the speed and accuracy of trainig.

Parameters:

p_learningRate - The learning rate

getLearningRate

public double getLearningRate()

Returns the current learning rate.

Returns:

The current learning rate.

backPropagateHidden

public void backPropagateHidden(NeuronLayer downstream,
                       ReceptiveNeuron[] neurons)

Back propagates a hidden layer relative to the layer immediately following it.

Specified by:

backPropagateHidden in interface BackPropagationMethod

Parameters:

downstream - The layer downstream from this

neurons - The neurons in the layer to backprop.

backPropagateOutputs

public double backPropagateOutputs(double[] desirable,
                          ReceptiveNeuron[] neurons)

This function back-propogates output nodes. It is subtly different to other Neuron layers' backprop algorithm and is called first by NeuralNet. It returns sum([delta]o/n), the sum of all error functions with respect to weightings on each output node. This returned value must be passed to the other node layers during the second stage of backprop training.

Specified by:

backPropagateOutputs in interface BackPropagationMethod

Parameters:

desirable - The desirable set of inputs to adapt to

neurons - The neurons to backpropagate

Returns:

The mean squared error for the whole net.

Throws:

IndexOutOfBoundsException - in the event that the number of desirable outputs does not match that of the net.