C# Class Encog.Neural.Networks.Synapse.NEAT.NEATSynapse

Implements a NEAT network as a synapse between two layers. In Encog, a NEAT network is created by using a NEATSynapse between an input and output layer. NEAT networks only have an input and an output layer. There are no actual hidden layers. Rather this synapse will evolve many hidden neurons that have connections that are not easily defined by layers. Connections can be feedforward, recurrent, or self-connected. NEAT networks relieve the programmer of the need to define the hidden layer structure of the neural network. The output from the neural network can be calculated normally or using a snapshot. The snapshot mode is slower, but it can be more accurate. The snapshot handles recurrent layers better, as it takes the time to loop through the network multiple times to "flush out" the recurrent links. NeuroEvolution of Augmenting Topologies (NEAT) is a genetic algorithm for the generation of evolving artificial neural networks. It was developed by Ken Stanley while at The University of Texas at Austin. http://www.cs.ucf.edu/~kstanley/
Inheritance: Encog.Persist.BasicPersistedSubObject, ISynapse, IContextClearable
Afficher le fichier Open project: encog/encog-silverlight-core Class Usage Examples

Méthodes publiques

Méthode Description
ClearContext ( ) : void

Clear any context.

Clone ( ) : object

A clone of this object.

Compute ( INeuralData input ) : INeuralData

Compute the output from this synapse.

CreatePersistor ( ) : IPersistor

A persistor to load/save this type of synapse.

NEATSynapse ( ) : System

Default constructor.

NEATSynapse ( ILayer fromLayer, ILayer toLayer ) : System

Create a NEAT synapse.

NEATSynapse ( ILayer fromLayer, ILayer toLayer, IList neurons, IActivationFunction activationFunction, int networkDepth ) : System

Construct a NEAT synapse.

getNeurons ( ) : IList

The NEAT neurons.

Method Details

ClearContext() public méthode

Clear any context.
public ClearContext ( ) : void
Résultat void

Clone() public méthode

A clone of this object.
public Clone ( ) : object
Résultat object

Compute() public méthode

Compute the output from this synapse.
public Compute ( INeuralData input ) : INeuralData
input INeuralData The input to this synapse.
Résultat INeuralData

CreatePersistor() public méthode

A persistor to load/save this type of synapse.
public CreatePersistor ( ) : IPersistor
Résultat IPersistor

NEATSynapse() public méthode

Default constructor.
public NEATSynapse ( ) : System
Résultat System

NEATSynapse() public méthode

Create a NEAT synapse.
public NEATSynapse ( ILayer fromLayer, ILayer toLayer ) : System
fromLayer ILayer The from layer.
toLayer ILayer The to layer.
Résultat System

NEATSynapse() public méthode

Construct a NEAT synapse.
public NEATSynapse ( ILayer fromLayer, ILayer toLayer, IList neurons, IActivationFunction activationFunction, int networkDepth ) : System
fromLayer ILayer The input layer.
toLayer ILayer The output layer.
neurons IList The neurons in this synapse.
activationFunction IActivationFunction The activation function to use.
networkDepth int The depth of the network.
Résultat System

getNeurons() public méthode

The NEAT neurons.
public getNeurons ( ) : IList
Résultat IList