Replacement for BackpropagationNetwork from NeuronDotNet, adapts some functionality to the needs of enclosing class.
More...
List of all members.
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)
|
| MyNeuronBackPropagation (SerializationInfo info, StreamingContext context) |
| Deserialization Constructor.
|
override void | Learn (TrainingSet trainingSet, int trainingEpochs) |
| Trains the neural network for the given training set (Batch Training)
|
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:
-
inputLayer | The input layer |
outputLayer | The output layer |
- Exceptions:
-
ArgumentNullException | If inputLayer or outputLayer is null |
IG::Neural::NeuralApproximatorNeuron::MyNeuronBackPropagation::MyNeuronBackPropagation |
( |
SerializationInfo |
info, |
|
|
StreamingContext |
context |
|
) |
| [inline] |
Deserialization Constructor.
- Parameters:
-
info | Serialization information to deserialize and obtain the data |
context | Serialization context to use |
- Exceptions:
-
ArgumentNullException | If 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:
-
trainingSet | The training set to use |
trainingEpochs | Number of training epochs. (All samples are trained in some random order, in every training epoch) |
- Exceptions:
-
ArgumentNullException | if trainingSet is null |
ArgumentException | if trainingEpochs is zero or negative |
The documentation for this class was generated from the following file: