C# Class Encog.Neural.Networks.Training.Lma.JacobianChainRule

Inheritance: IComputeJacobian
Mostrar archivo Open project: encog/encog-silverlight-core Class Usage Examples

Public Methods

Method Description
Calculate ( double weights ) : double

Calculate the Jacobian matrix.

JacobianChainRule ( BasicNetwork network, IMLDataSet indexableTraining ) : Encog.Engine.Network.Activation

Construct the chain rule calculation.

Private Methods

Method Description
CalcDerivative ( IActivationFunction a, double d ) : double

Calculate the derivative.

CalcDerivative2 ( IActivationFunction a, double d ) : double

Calculate the derivative.

CalculateDerivatives ( IMLDataPair pair ) : double

Calculate the derivatives for this training set element.

Method Details

Calculate() public method

Calculate the Jacobian matrix.
public Calculate ( double weights ) : double
weights double The weights for the neural network.
return double

JacobianChainRule() public method

Construct the chain rule calculation.
public JacobianChainRule ( BasicNetwork network, IMLDataSet indexableTraining ) : Encog.Engine.Network.Activation
network Encog.Neural.Networks.BasicNetwork The network to use.
indexableTraining IMLDataSet The training set to use.
return Encog.Engine.Network.Activation