Package me.damoebe.architectures.mlp

Class 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

Field Summary

Fields inherited from class me.damoebe.architectures.mlp.FFNetwork

currentLoss, layers, learningRate, noise

Constructor Summary

Constructors

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

Method Summary

Modifier and Type	Method	Description
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.

Methods inherited from class me.damoebe.architectures.mlp.FFNetwork

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

Methods inherited from class me.damoebe.architectures.Network

loadNetworkFromJson, loadToJsonFile

Methods inherited from class java.lang.Object

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

Constructor Details

DeepNetwork

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

Main constructor for DeepNetwork calling the super constructor

Parameters:

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

Method Details

train

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

Trains the network with one set of data using backpropagation.

Specified by:

train in class FFNetwork

Parameters:

input - The inputs for this repetition

optimalOutput - The optimalOutputs for this repetition

getNetworkLoss

public double getNetworkLoss()

Gets the network loss

Specified by:

getNetworkLoss in class FFNetwork

Returns:

The network loss

clone

public FFNetwork clone()

Description copied from class: FFNetwork

A method for cloning a FFNetwork object

Specified by:

clone in class FFNetwork

Returns:

the cloned network object