C# Class Accord.Math.Optimization.ResilientBackpropagation

Resilient Backpropagation method for unconstrained optimization.

Inheritance: BaseGradientOptimizationMethod, IGradientOptimizationMethod

Public Methods

Method	Description
Reset ( double rate ) : void	Resets the current update steps using the given learning rate.
ResilientBackpropagation ( NonlinearObjectiveFunction function ) : System	Creates a new instance of the L-BFGS optimization algorithm.
ResilientBackpropagation ( int numberOfVariables ) : System	Creates a new ResilientBackpropagation function optimizer.
ResilientBackpropagation ( int numberOfVariables, double>.Func function, double[]>.Func gradient ) : System	Creates a new instance of the L-BFGS optimization algorithm.

Method	Description
OnProgressChanged ( ProgressChangedEventArgs args ) : void	Raises the E:ProgressChanged event.
Optimize ( ) : bool	Implements the actual optimization algorithm. This method should try to minimize the objective function.

Method	Description
init ( int numberOfVariables ) : void
runEpoch ( ) : double

Raises the E:ProgressChanged event.

protected OnProgressChanged ( ProgressChangedEventArgs args ) : void
args	System.ComponentModel.ProgressChangedEventArgs	The instance containing the event data.
return	void

Implements the actual optimization algorithm. This method should try to minimize the objective function.

protected Optimize ( ) : bool
return	bool

Resets the current update steps using the given learning rate.

public Reset ( double rate ) : void
rate	double
return	void

Creates a new instance of the L-BFGS optimization algorithm.

public ResilientBackpropagation ( NonlinearObjectiveFunction function ) : System
function	NonlinearObjectiveFunction	The function to be optimized.
return	System

Creates a new ResilientBackpropagation function optimizer.

public ResilientBackpropagation ( int numberOfVariables ) : System
numberOfVariables	int	The number of parameters in the function to be optimized.
return	System

Creates a new instance of the L-BFGS optimization algorithm.

public ResilientBackpropagation ( int numberOfVariables, double>.Func function, double[]>.Func gradient ) : System
numberOfVariables	int	The number of free parameters in the function to be optimized.
function	double>.Func	The function to be optimized.
gradient	double[]>.Func	The gradient of the function.
return	System