Click or drag to resize
ITrainer Interface
Interface implemented by classes used to train an Network.

Namespace: Imsl.DataMining.Neural
Assembly: ImslCS (in ImslCS.dll) Version: 6.5.2.0
Syntax
Copy
public interface ITrainer

The ITrainer type exposes the following members.

Methods
  NameDescription
Public methodTrain
Trains the neural network using supplied training patterns.
Top
Properties
  NameDescription
Public propertyErrorGradient
The value of the gradient of the error function with respect to the Weights.
Public propertyErrorStatus
The error status.
Public propertyErrorValue
The value of the error function minimized by the trainer.
Top
Remarks

The method Train is used to adjust the Weights in a network to best fit a set of observed data. After a Network is trained, the other methods in this interface can be used to check the quality of the fit.

See Also