org.ea.javacnn.layers

Class FullyConnectedLayer

java.lang.Object

org.ea.javacnn.layers.FullyConnectedLayer

All Implemented Interfaces:

java.io.Serializable, Layer

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

Neurons in a fully connected layer have full connections to all activations in the previous layer, as seen in regular Neural Networks. Their activations can hence be computed with a matrix multiplication followed by a bias offset.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
FullyConnectedLayer(OutputDefinition def, int num_neurons)

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

FullyConnectedLayer

public FullyConnectedLayer(OutputDefinition def,
                           int num_neurons)

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