IterativeLearning (Core 2.96 API)

java.lang.Object
- org.neuroph.core.learning.LearningRule
- - org.neuroph.core.learning.IterativeLearning

All Implemented Interfaces:

Serializable

Direct Known Subclasses:

SupervisedLearning, UnsupervisedLearning
```
public abstract class IterativeLearning
extends LearningRule
implements Serializable
```
Base class for all iterative learning algorithms. It provides the iterative learning procedure for all of its subclasses.

Author:

Zoran Sevarac

See Also:

Serialized Form

Field Summary

Fields
Modifier and Type	Field and Description
`protected int`	`currentIteration` Current iteration counter
`protected double`	`learningRate` Learning rate parametar
`protected List<StopCondition>`	`stopConditions`

Fields inherited from class org.neuroph.core.learning.LearningRule
listeners, neuralNetwork, trainingSet

Constructor Summary

Constructors
Constructor and Description

IterativeLearning()
Creates new instance of IterativeLearning learning algorithm

Constructors
Constructor and Description
`IterativeLearning()` Creates new instance of IterativeLearning learning algorithm

Method Summary

All Methods Instance Methods Abstract Methods Concrete Methods
Modifier and Type	Method and Description
`protected void`	`afterEpoch()`
`protected void`	`beforeEpoch()`
`abstract void`	`doLearningEpoch(DataSet trainingSet)` Override this method to implement specific learning epoch - one learning iteration, one pass through whole training set
`void`	`doOneLearningIteration(DataSet trainingSet)` Runs one learning iteration with the specified training set and fires event to notify observers.
`int`	`getCurrentIteration()` Returns current iteration of this learning algorithm
`double`	`getLearningRate()` Returns learning rate for this algorithm
`int`	`getMaxIterations()` Returns max iterations limit of this learning algorithm
`protected boolean`	`hasReachedStopCondition()` Returns true if any of the stop conditions has been reached.
`boolean`	`isIterationsLimited()`
`boolean`	`isPausedLearning()` Returns true if learning thread is paused, false otherwise
`void`	`learn(DataSet trainingSet)` Override this method to implement specific learning procedures
`void`	`learn(DataSet trainingSet, int maxIterations)` Trains network for the specified training set and number of iterations
`protected void`	`onStart()` This method is executed when learning starts, before the first epoch.
`void`	`pause()` Pause the learning
`void`	`resume()` Resumes the paused learning
`void`	`setLearningRate(double learningRate)` Sets learning rate for this algorithm
`void`	`setMaxIterations(int maxIterations)` Sets iteration limit for this learning algorithm

Methods inherited from class org.neuroph.core.learning.LearningRule
addListener, fireLearningEvent, getNeuralNetwork, getTrainingSet, isStopped, onStop, removeListener, setNeuralNetwork, setTrainingSet, stopLearning

Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

- Field Detail
  - learningRate
```
protected double learningRate
```
    Learning rate parametar
  - currentIteration
```
protected int currentIteration
```
    Current iteration counter
  - stopConditions
```
protected List<StopCondition> stopConditions
```
- Constructor Detail
  - IterativeLearning
```
public IterativeLearning()
```
    Creates new instance of IterativeLearning learning algorithm
- Method Detail
  - getLearningRate
```
public double getLearningRate()
```
    Returns learning rate for this algorithm
    
    Returns:
    
    learning rate for this algorithm
  - setLearningRate
```
public void setLearningRate(double learningRate)
```
    Sets learning rate for this algorithm
    
    Parameters:
    
    learningRate - learning rate for this algorithm
  - setMaxIterations
```
public void setMaxIterations(int maxIterations)
```
    Sets iteration limit for this learning algorithm
    
    Parameters:
    
    maxIterations - iteration limit for this learning algorithm
  - getMaxIterations
```
public int getMaxIterations()
```
    Returns max iterations limit of this learning algorithm
    
    Returns:
    
    max iteration limit of this learning algorithm
  - isIterationsLimited
```
public boolean isIterationsLimited()
```
  - getCurrentIteration
```
public int getCurrentIteration()
```
    Returns current iteration of this learning algorithm
    
    Returns:
    
    current iteration of this learning algorithm
  - isPausedLearning
```
public boolean isPausedLearning()
```
    Returns true if learning thread is paused, false otherwise
    
    Returns:
    
    true if learning thread is paused, false otherwise
  - pause
```
public final void pause()
```
    Pause the learning
  - resume
```
public final void resume()
```
    Resumes the paused learning
  - onStart
```
protected void onStart()
```
    This method is executed when learning starts, before the first epoch. Used for initialisation.
    
    Overrides:
    
    onStart in class LearningRule
  - beforeEpoch
```
protected void beforeEpoch()
```
  - afterEpoch
```
protected void afterEpoch()
```
  - learn
```
public final void learn(DataSet trainingSet)
```
    Description copied from class: LearningRule
    
    Override this method to implement specific learning procedures
    
    Specified by:
    
    learn in class LearningRule
    
    Parameters:
    
    trainingSet - training set
  - hasReachedStopCondition
```
protected final boolean hasReachedStopCondition()
```
    Returns true if any of the stop conditions has been reached.
    
    Returns:
  - learn
```
public void learn(DataSet trainingSet,
                  int maxIterations)
```
    Trains network for the specified training set and number of iterations
    
    Parameters:
    
    trainingSet - training set to learn
    
    maxIterations - maximum numberof iterations to learn
  - doOneLearningIteration
```
public void doOneLearningIteration(DataSet trainingSet)
```
    Runs one learning iteration with the specified training set and fires event to notify observers. This method does the the doLearningEpoch() and in addtion notifes observrs when iteration is done.
    
    Parameters:
    
    trainingSet - training set to learn
  - doLearningEpoch
```
public abstract void doLearningEpoch(DataSet trainingSet)
```
    Override this method to implement specific learning epoch - one learning iteration, one pass through whole training set
    
    Parameters:
    
    trainingSet - training set

Class IterativeLearning

Field Summary

Fields inherited from class org.neuroph.core.learning.LearningRule

Constructor Summary

Method Summary

Methods inherited from class org.neuroph.core.learning.LearningRule

Methods inherited from class java.lang.Object

Field Detail

learningRate

currentIteration

stopConditions

Constructor Detail

IterativeLearning

Method Detail

getLearningRate

setLearningRate

setMaxIterations

getMaxIterations

isIterationsLimited

getCurrentIteration

isPausedLearning

pause

resume

onStart

beforeEpoch

afterEpoch

learn

hasReachedStopCondition

learn

doOneLearningIteration

doLearningEpoch