org.ea.javacnn.losslayers

Class RegressionLayer

java.lang.Object

org.ea.javacnn.losslayers.LossLayer

org.ea.javacnn.losslayers.RegressionLayer

All Implemented Interfaces:

java.io.Serializable, Layer

public class RegressionLayer
extends LossLayer

Regression layer is used when your output is an area of data. When you don't have a single class that is the correct activation but you try to find a result set near to your training area.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
RegressionLayer(OutputDefinition def)

Method Summary

Modifier and Type	Method and Description
double	backward(double[] y)
double	backward(int y)
DataBlock	forward(DataBlock db, boolean training)

Methods inherited from class org.ea.javacnn.losslayers.LossLayer

backward, getBackPropagationResult, getOutAct

Methods inherited from class java.lang.Object

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

Constructor Detail

RegressionLayer

public RegressionLayer(OutputDefinition def)

Method Detail

forward

public DataBlock forward(DataBlock db,
                         boolean training)

backward

public double backward(double[] y)

backward

public double backward(int y)

Specified by:

backward in class LossLayer