QuasiNewtonTrainer.UseBackPropagation Property

QuasiNewtonTrainerUseBackPropagation Property

Specify the use of the back propagation algorithm for gradient calculations during network training.

Namespace: Imsl.DataMining.Neural
Assembly: ImslCS (in ImslCS.dll) Version: 6.5.2.0

Syntax

public virtual bool UseBackPropagation { get; set; }

Public Overridable Property UseBackPropagation As Boolean
	Get
	Set

public:
virtual property bool UseBackPropagation {
	bool get ();
	void set (bool value);
}

abstract UseBackPropagation : bool with get, set
override UseBackPropagation : bool with get, set

Property Value

Type: Boolean
A bool specifying whether or not back propagation is used for gradient calculations. By default, UseBackPropagation = true.

Remarks

By default, the quasi-newton algorithm optimizes the network using numerical gradients. This method directs the quasi-newton trainer to use the back propagation algorithm for gradient calculations during network training. Depending upon the data and network architecture, one approach is typically faster than the other, or is less sensitive to finding local network optima.

Reference

QuasiNewtonTrainer Class

Imsl.DataMining.Neural Namespace