org.encog.neural.data
Interface NeuralDataSet

All Superinterfaces:

EngineDataSet, Iterable<NeuralDataPair>

All Known Subinterfaces:

Indexable

All Known Implementing Classes:

BasicNeuralDataSet, BufferedNeuralDataSet, CSVNeuralDataSet, FoldedDataSet, ImageNeuralDataSet, MarketNeuralDataSet, SQLNeuralDataSet, TemporalNeuralDataSet, UnionNeuralDataSet, XMLNeuralDataSet

public interface NeuralDataSet
extends Iterable<NeuralDataPair>, EngineDataSet

An interface designed to abstract classes that store neural data. This interface is designed to provide NeuralDataPair objects. This can be used to train neural networks using both supervised and unsupervised training. Some implementations of this interface are memory based. That is they store the entire contents of the dataset in memory. Other implementations of this interface are not memory based. These implementations read in data as it is needed. This allows very large datasets to be used. Typically the add methods are not supported on non-memory based datasets.

Author:

jheaton

Method Summary

void	add(NeuralData data1) Add a NeuralData object to the dataset.
void	add(NeuralData inputData, NeuralData idealData) Add a set of input and ideal data to the dataset.
void	add(NeuralDataPair inputData) Add a NeuralData object to the dataset.
void	close() Close this datasource and release any resources obtained by it, including any iterators created.
int	getIdealSize()
int	getInputSize()
boolean	isSupervised()

Methods inherited from interface java.lang.Iterable

iterator

Method Detail

add

void add(NeuralData data1)

Add a NeuralData object to the dataset. This is used with unsupervised training, as no ideal output is provided. Note: not all implemenations support the add methods.

Parameters:

data1 - The data item to be added.

add

void add(NeuralData inputData,
         NeuralData idealData)

Add a set of input and ideal data to the dataset. This is used with supervised training, as ideal output is provided. Note: not all implementations support the add methods.

Parameters:

inputData - Input data.

idealData - Ideal data.

add

void add(NeuralDataPair inputData)

Add a NeuralData object to the dataset. This is used with unsupervised training, as no ideal output is provided. Note: not all implementations support the add methods.

Parameters:

inputData - A NeuralDataPair object that contains both input and ideal data.

close

void close()

Close this datasource and release any resources obtained by it, including any iterators created.

getIdealSize

int getIdealSize()

Specified by:

getIdealSize in interface EngineDataSet

Returns:

The size of the input data.

getInputSize

int getInputSize()

Specified by:

getInputSize in interface EngineDataSet

Returns:

The size of the input data.

isSupervised

boolean isSupervised()

Specified by:

isSupervised in interface EngineDataSet

Returns:

True if this is a supervised training set.