org.encog.neural.data
Interface NeuralDataPair
- All Known Implementing Classes:
- BasicNeuralDataPair
public interface NeuralDataPair
Training data is stored in two ways, depending on if the data is for
supervised, or unsupervised training.
For supervised training just an input value is provided, and the
ideal output values are null.
For unsupervised training both input and the expected ideal outputs
are provided.
This interface abstracts classes that provide a holder for both of
these two data items.
- Author:
- jheaton
getInput
NeuralData getInput()
- Returns:
- The input that the neural network
getIdeal
NeuralData getIdeal()
- Returns:
- The ideal data that the neural network should produce
for the specified input.
isSupervised
boolean isSupervised()
- Returns:
- True if this training pair is supervised. That is, it has
both input and ideal data.