deepnetts.net.layers

Class OutputLayer

java.lang.Object

deepnetts.net.layers.AbstractLayer

deepnetts.net.layers.OutputLayer

All Implemented Interfaces:

Layer, Serializable

Direct Known Subclasses:

SoftmaxOutputLayer

public class OutputLayer
extends AbstractLayer

Output layer of a neural network. It is always the last layer in a neural network, and gives the final output of a network.

Author:

Zoran Sevarac

See Also:

AbstractLayer, Layer, NeuralNetwork, Serialized Form

Constructor Summary

Constructors

Constructor and Description
OutputLayer(int width) Creates an instance of output layer with specified width (number of outputs) and sigmoid activation function by default.
OutputLayer(int width, ActivationType actType) Creates an instance of output layer with specified width (number of outputs) and specified activation function.
OutputLayer(String[] outputLabels) Creates an instance of output layer with specified width (number of outputs) which corresponds to number of labels and sigmoid activation function by default.
OutputLayer(String[] outputLabels, ActivationType actType)

Method Summary

Modifier and Type	Method and Description
void	applyWeightChanges() Applies weight changes after one learning iteration or batch
void	backward() This method implements backward pass for the output layer.
void	forward() This method implements forward pass for the output layer.
LossType	getLossType()
float[]	getOutputErrors()
float	getSingleOutInput()
void	init() This method should implement layer initialization in subclasses, when a layer is added to the network (create weights, outputs, deltas, randomization etc.).
void	setLossType(LossType lossType)
void	setOutputErrors(float[] outputErrors)
String	toString()

Methods inherited from class deepnetts.net.layers.AbstractLayer

getActivation, getActivationType, getBatchSize, getBiases, getDeltaBiases, getDeltas, getDeltaWeights, getDepth, getGradients, getHeight, getL1Regularization, getL1WeightSum, getL2Regularization, getL2WeightSum, getLearningRate, getMomentum, getNextLayer, getOptimizer, getOptimizerType, getOutputs, getPrevDeltaBiases, getPrevDeltaWeights, getPrevlayer, getWeights, getWidth, initTransientFields, isBatchMode, isTrainable, setBatchMode, setBatchSize, setBiases, setDeltas, setL1Regularization, setL2Regularization, setLearningRate, setMomentum, setNextlayer, setOptimizerType, setOutputs, setPrevDeltaWeights, setPrevLayer, setTrainable, setWeights, setWeights

Methods inherited from class java.lang.Object

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

Constructor Detail

OutputLayer

public OutputLayer(int width)

Creates an instance of output layer with specified width (number of outputs) and sigmoid activation function by default. Outputs are labeled using generic names "Output1, 2, 3..."

Parameters:

width - layer width which represents number of network outputs

OutputLayer

public OutputLayer(int width,
                   ActivationType actType)

Creates an instance of output layer with specified width (number of outputs) and specified activation function. Outputs are labeled using generic names "Output1, 2, 3..."

Parameters:

width - layer width whic represents number of network outputs

actType - activation function

OutputLayer

public OutputLayer(String[] outputLabels)

Creates an instance of output layer with specified width (number of outputs) which corresponds to number of labels and sigmoid activation function by default. Outputs are labeled with strings specified in labels parameter

Parameters:

outputLabels - labels for network's outputs

OutputLayer

public OutputLayer(String[] outputLabels,
                   ActivationType actType)

Method Detail

setOutputErrors

public final void setOutputErrors(float[] outputErrors)

getOutputErrors

public final float[] getOutputErrors()

getLossType

public final LossType getLossType()

setLossType

public void setLossType(LossType lossType)

init

public void init()

Description copied from class: AbstractLayer

This method should implement layer initialization in subclasses, when a layer is added to the network (create weights, outputs, deltas, randomization etc.).

Specified by:

init in class AbstractLayer

forward

public void forward()

This method implements forward pass for the output layer. Calculates weighted input and layer outputs using sigmoid function.

Specified by:

forward in interface Layer

Specified by:

forward in class AbstractLayer

backward

public void backward()

This method implements backward pass for the output layer. http://peterroelants.github.io/posts/neural_network_implementation_intermezzo01/ http://neuralnetworksanddeeplearning.com/chap3.html#introducing_the_cross-entropy_cost_function

Specified by:

backward in interface Layer

Specified by:

backward in class AbstractLayer

applyWeightChanges

public void applyWeightChanges()

Applies weight changes after one learning iteration or batch

Specified by:

applyWeightChanges in class AbstractLayer

toString

public String toString()

Overrides:

toString in class Object

getSingleOutInput

public float getSingleOutInput()