IGLib  1.7.2
The IGLib base library EXTENDED - with other lilbraries and applications.
 All Classes Namespaces Files Functions Variables Typedefs Enumerations Enumerator Properties Events Macros
IG.Neural.NeuralApproximatorNeuron.MyNeuronBackPropagation Class Reference

Replacement for BackpropagationNetwork from NeuronDotNet, adapts some functionality to the needs of enclosing class. More...

+ Inheritance diagram for IG.Neural.NeuralApproximatorNeuron.MyNeuronBackPropagation:
+ Collaboration diagram for IG.Neural.NeuralApproximatorNeuron.MyNeuronBackPropagation:

Public Member Functions

 MyNeuronBackPropagation (NeuronDotNet.Core.Backpropagation.ActivationLayer inputLayer, NeuronDotNet.Core.Backpropagation.ActivationLayer outputLayer)
 Creates a new Back Propagation Network, with the specified input and output layers. (You are required to connect all layers using appropriate synapses, before using the constructor. Any changes made to the structure of the network after its creation may lead to complete malfunctioning) More...
 
 MyNeuronBackPropagation (SerializationInfo info, StreamingContext context)
 Deserialization Constructor More...
 
override void Learn (TrainingSet trainingSet, int trainingEpochs)
 Trains the neural network for the given training set (Batch Training) More...
 

Detailed Description

Replacement for BackpropagationNetwork from NeuronDotNet, adapts some functionality to the needs of enclosing class.

$A Igor Jul26;

Constructor & Destructor Documentation

IG.Neural.NeuralApproximatorNeuron.MyNeuronBackPropagation.MyNeuronBackPropagation ( NeuronDotNet.Core.Backpropagation.ActivationLayer  inputLayer,
NeuronDotNet.Core.Backpropagation.ActivationLayer  outputLayer 
)
inline

Creates a new Back Propagation Network, with the specified input and output layers. (You are required to connect all layers using appropriate synapses, before using the constructor. Any changes made to the structure of the network after its creation may lead to complete malfunctioning)

Parameters
inputLayerThe input layer
outputLayerThe output layer
Exceptions
ArgumentNullExceptionIf inputLayer or outputLayer is null
IG.Neural.NeuralApproximatorNeuron.MyNeuronBackPropagation.MyNeuronBackPropagation ( SerializationInfo  info,
StreamingContext  context 
)
inline

Deserialization Constructor

Parameters
infoSerialization information to deserialize and obtain the data
contextSerialization context to use
Exceptions
ArgumentNullExceptionIf info is null

Member Function Documentation

override void IG.Neural.NeuralApproximatorNeuron.MyNeuronBackPropagation.Learn ( TrainingSet  trainingSet,
int  trainingEpochs 
)
inline

Trains the neural network for the given training set (Batch Training)

Parameters
trainingSetThe training set to use
trainingEpochsNumber of training epochs. (All samples are trained in some random order, in every training epoch)
Exceptions
ArgumentNullExceptionif trainingSet is null
ArgumentExceptionif trainingEpochs is zero or negative

Referenced by IG.Neural.NeuralApproximatorNeuron.TrainNetworkSpecific().


The documentation for this class was generated from the following file: