Package me.damoebe.architectures.mlp

Klasse EvolutionNetwork

java.lang.Object

me.damoebe.architectures.Network

me.damoebe.architectures.mlp.FFNetwork

me.damoebe.architectures.mlp.EvolutionNetwork

public class EvolutionNetwork
extends FFNetwork

An object class for EvolutionNetworks

Feldübersicht

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

currentLoss, layers, learningRate, noise

Konstruktorübersicht

Konstruktoren

Konstruktor	Beschreibung
EvolutionNetwork(int inputSize, int outputSize, int hiddenLayerSize, int hiddenLayerAmount)	Main constructor for EvolutionNetwork accessing the super constructor of FFNetwork abstract class

Methodenübersicht

Modifizierer und Typ	Methode	Beschreibung
FFNetwork	clone()	A method for cloning a FFNetwork object
void	finishEpoch()	Finishes an epoch by saving potential success and mutating connection weights
double	getNetworkLoss()	Gets the network loss
void	train(List<Double> input, List<Double> optimalOutput)	The abstract train function
void	updateLoss(List<Double> optimalActivations)	Updates the current network loss and adds loss to epoch loss list

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

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

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

EvolutionNetwork

public EvolutionNetwork(int inputSize,
 int outputSize,
 int hiddenLayerSize,
 int hiddenLayerAmount)

Main constructor for EvolutionNetwork accessing the super constructor of FFNetwork abstract class

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

Methodendetails

train

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

Beschreibung aus Klasse kopiert: FFNetwork

The abstract train function

Angegeben von:

train in Klasse FFNetwork

Parameter:

input - The inputs for this repetition

optimalOutput - The optimalOutputs for this repetition

updateLoss

public void updateLoss(List<Double> optimalActivations)

Updates the current network loss and adds loss to epoch loss list

Setzt außer Kraft:

updateLoss in Klasse FFNetwork

Parameter:

optimalActivations - The target activations for the current repetition

finishEpoch

public void finishEpoch()

Finishes an epoch by saving potential success and mutating connection weights

getNetworkLoss

public double getNetworkLoss()

Beschreibung aus Klasse kopiert: FFNetwork

Gets the network loss

Angegeben von:

getNetworkLoss in Klasse FFNetwork

Gibt zurück:

The network loss double

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