Package me.damoebe.architectures.mlp

Klasse DeepNetwork

java.lang.Object

me.damoebe.architectures.Network

me.damoebe.architectures.mlp.FFNetwork

me.damoebe.architectures.mlp.DeepNetwork

public class DeepNetwork
extends FFNetwork

An object class for DeepNetwork objects

Feldübersicht

Von Klasse geerbte Felder me.damoebe.architectures.mlp.FFNetwork

currentLoss, layers, learningRate, noise

Konstruktorübersicht

Konstruktoren

Konstruktor	Beschreibung
DeepNetwork(int inputSize, int outputSize, int hiddenLayerSize, int hiddenLayerAmount, double leaningRate)	Main constructor for DeepNetwork calling the super constructor

Methodenübersicht

Modifizierer und Typ	Methode	Beschreibung
FFNetwork	clone()	A method for cloning a FFNetwork object
double	getNetworkLoss()	Gets the network loss
void	train(List<Double> input, List<Double> optimalOutput)	Trains the network with one set of data using backpropagation.

Von Klasse geerbte Methoden me.damoebe.architectures.mlp.FFNetwork

generateLayer, getHiddenLayerAmount, getHiddenLayerSize, getInputSize, getLayers, getOutput, getOutputSize, insertInput, setNoise, updateAllActivations, updateLoss

Von Klasse geerbte Methoden me.damoebe.architectures.Network

loadNetworkFromJson, loadToJsonFile

Von Klasse geerbte Methoden java.lang.Object

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

Konstruktordetails

DeepNetwork

public DeepNetwork(int inputSize,
 int outputSize,
 int hiddenLayerSize,
 int hiddenLayerAmount,
 double leaningRate)

Main constructor for DeepNetwork calling the super constructor

Parameter:

inputSize - The size of the first layer

outputSize - The size of the last layer

hiddenLayerSize - The size of the hiddenlayers

hiddenLayerAmount - The amount of hiddenlayers that should be generated

leaningRate - The learningRate that should be used for this DeepNetwork

Methodendetails

train

public void train(List<Double> input,
 List<Double> optimalOutput)

Trains the network with one set of data using backpropagation.

Angegeben von:

train in Klasse FFNetwork

Parameter:

input - The inputs for this repetition

optimalOutput - The optimalOutputs for this repetition

getNetworkLoss

public double getNetworkLoss()

Gets the network loss

Angegeben von:

getNetworkLoss in Klasse FFNetwork

Gibt zurück:

The network loss

clone

public FFNetwork clone()

Beschreibung aus Klasse kopiert: FFNetwork

A method for cloning a FFNetwork object

Angegeben von:

clone in Klasse FFNetwork

Gibt zurück:

the cloned network object