org.ea.javacnn.layers

Class LocalResponseNormalizationLayer

java.lang.Object

org.ea.javacnn.layers.LocalResponseNormalizationLayer

All Implemented Interfaces:

java.io.Serializable, Layer

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

This layer is useful when we are dealing with ReLU neurons. Why is that? Because ReLU neurons have unbounded activations and we need LRN to normalize that. We want to detect high frequency features with a large response. If we normalize around the local neighborhood of the excited neuron, it becomes even more sensitive as compared to its neighbors. At the same time, it will dampen the responses that are uniformly large in any given local neighborhood. If all the values are large, then normalizing those values will diminish all of them. So basically we want to encourage some kind of inhibition and boost the neurons with relatively larger activations. This has been discussed nicely in Section 3.3 of the original paper by Krizhevsky et al.

See Also:

Serialized Form

Constructor Summary

Constructors

Constructor and Description
LocalResponseNormalizationLayer()

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

LocalResponseNormalizationLayer

public LocalResponseNormalizationLayer()

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