org.ea.javacnn.layers

Class RectifiedLinearUnitsLayer

java.lang.Object

org.ea.javacnn.layers.RectifiedLinearUnitsLayer

All Implemented Interfaces:

java.io.Serializable, Layer

public class RectifiedLinearUnitsLayer
extends java.lang.Object
implements Layer, java.io.Serializable

This is a layer of neurons that applies the non-saturating activation function f(x)=max(0,x). It increases the nonlinear properties of the decision function and of the overall network without affecting the receptive fields of the convolution layer.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
RectifiedLinearUnitsLayer()

Method Summary

Modifier and Type	Method and Description
void	backward()
DataBlock	forward(DataBlock db, boolean training)
java.util.List<BackPropResult>	getBackPropagationResult()

Methods inherited from class java.lang.Object

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

Constructor Detail

RectifiedLinearUnitsLayer

public RectifiedLinearUnitsLayer()

Method Detail

forward

public DataBlock forward(DataBlock db,
                         boolean training)

Specified by:

forward in interface Layer

backward

public void backward()

Specified by:

backward in interface Layer

getBackPropagationResult

public java.util.List<BackPropResult> getBackPropagationResult()

Specified by:

getBackPropagationResult in interface Layer