Package me.damoebe.architectures.mlp
Klasse DeepNetwork
java.lang.Object
me.damoebe.architectures.Network
me.damoebe.architectures.mlp.FFNetwork
me.damoebe.architectures.mlp.DeepNetwork
-
Feldübersicht
Von Klasse geerbte Felder me.damoebe.architectures.mlp.FFNetwork
currentLoss, layers, learningRate, noise -
Konstruktorübersicht
KonstruktorenKonstruktorBeschreibungDeepNetwork(int inputSize, int outputSize, int hiddenLayerSize, int hiddenLayerAmount, double leaningRate) Main constructor for DeepNetwork calling the super constructor -
Methodenübersicht
Von Klasse geerbte Methoden me.damoebe.architectures.mlp.FFNetwork
generateLayer, getHiddenLayerAmount, getHiddenLayerSize, getInputSize, getLayers, getOutput, getOutputSize, insertInput, setNoise, updateAllActivations, updateLossVon Klasse geerbte Methoden me.damoebe.architectures.Network
loadNetworkFromJson, loadToJsonFile
-
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 layeroutputSize- The size of the last layerhiddenLayerSize- The size of the hiddenlayershiddenLayerAmount- The amount of hiddenlayers that should be generatedleaningRate- The learningRate that should be used for this DeepNetwork
-
-
Methodendetails
-
train
-
getNetworkLoss
public double getNetworkLoss()Gets the network loss- Angegeben von:
getNetworkLossin KlasseFFNetwork- Gibt zurück:
- The network loss
-
clone
-