C# Class Encog.Neural.Pattern.JordanPattern

This class is used to generate an Jordan style recurrent neural network. This network type consists of three regular layers, an input output and hidden layer. There is also a context layer which accepts output from the output layer and outputs back to the hidden layer. This makes it a recurrent neural network. The Jordan neural network is useful for temporal input data. The specified activation function will be used on all layers. The Jordan neural network is similar to the Elman neural network.
Inheritance: INeuralNetworkPattern
ファイルを表示 Open project: encog/encog-silverlight-core Class Usage Examples

Public Methods

Method Description
AddHiddenLayer ( int count ) : void

Add a hidden layer, there should be only one.
Clear ( ) : void

Clear out any hidden neurons.
Generate ( ) : IMLMethod

Generate a Jordan neural network.
JordanPattern ( ) : Encog.Engine.Network.Activation

Construct an object to create a Jordan type neural network.

Method Details

AddHiddenLayer() public method

Add a hidden layer, there should be only one.
public AddHiddenLayer ( int count ) : void
count int The number of neurons in this hidden layer.
return void

Clear() public method

Clear out any hidden neurons.
public Clear ( ) : void
return void

Generate() public method

Generate a Jordan neural network.
public Generate ( ) : IMLMethod
return IMLMethod

JordanPattern() public method

Construct an object to create a Jordan type neural network.
public JordanPattern ( ) : Encog.Engine.Network.Activation
return Encog.Engine.Network.Activation