public class Backpropagation extends GradientDescent
P
is the number of data examples.DEFAULT_LEARNING_RATE, DEFAULT_MOMENTUM
Constructor and Description |
---|
Backpropagation(FeedforwardNet network)
Creates a new object using default learning rate and momentum values.
|
Backpropagation(FeedforwardNet network,
double learningRate,
double momentum)
Creates a new object using provided learning rate and momentum values.
|
Modifier and Type | Method and Description |
---|---|
FeedforwardNet |
getNetwork()
Returns a network trained by this rule.
|
protected void |
trainExample(DataExample example)
Learns a single pattern.
|
getCurrentError, getCurrentIteration, getLastError, getLearningRate, getMomentum, getStopCondition, setCurrentError, setLearningRate, setMomentum, setStopCondition, train
public Backpropagation(FeedforwardNet network)
public Backpropagation(FeedforwardNet network, double learningRate, double momentum)
learningRate
- the learning rate valuemomentum
- the momentum valuepublic final FeedforwardNet getNetwork()
TrainingRule
protected final void trainExample(DataExample example)
trainExample
in class GradientDescent
example
- Copyright © 2012. All Rights Reserved.