The QuasiNewtonTrainer type exposes the following members.
Constructors
Name | Description | |
---|---|---|
QuasiNewtonTrainer |
Constructs a QuasiNewtonTrainer object.
|
Methods
Name | Description | |
---|---|---|
Clone |
Clones a copy of the trainer.
| |
Equals | (Inherited from Object.) | |
Finalize |
Allows an Object to attempt to free resources and perform other cleanup operations before the Object is reclaimed by garbage collection.
(Inherited from Object.) | |
GetError |
Returns the function used to compute the error to be minimized.
| |
GetHashCode |
Serves as a hash function for a particular type.
(Inherited from Object.) | |
GetType |
Gets the Type of the current instance.
(Inherited from Object.) | |
MemberwiseClone |
Creates a shallow copy of the current Object.
(Inherited from Object.) | |
SetError |
Sets the function that computes the network error.
| |
ToString | (Inherited from Object.) | |
Train |
Trains the neural network using supplied training patterns.
|
Fields
Name | Description | |
---|---|---|
SUM_OF_SQUARES |
Compute the sum of squares error.
|
Properties
Name | Description | |
---|---|---|
EpochNumber |
The epoch number for the trainer.
| |
Error |
The error function used by the trainer.
| |
ErrorGradient |
The value of the gradient of the error function with respect to the
Weights.
| |
ErrorStatus |
The error status from the trainer.
| |
ErrorValue |
The final value of the error function.
| |
GradientTolerance |
The gradient tolerance.
| |
MaximumStepsize |
The maximum step size.
| |
MaximumTrainingIterations |
The maximum number of iterations to use in a training.
| |
NumberOfProcessors |
Perform the parallel calculations with the maximum possible number of
processors set to NumberOfProcessors.
| |
ParallelMode |
The trainer to be used in multi-threaded EpochTainer.
| |
StepTolerance |
The scaled step tolerance.
| |
TrainingIterations |
The number of iterations used during training.
| |
UseBackPropagation |
Specify the use of the back propagation algorithm for gradient
calculations during network training.
|