FFNet Class |
Namespace: FinMath.MachineLearning.NeuralNetworks
[SerializableAttribute] public abstract class FFNet : IDisposable, ISerializable
The FFNet type exposes the following members.
Name | Description | |
---|---|---|
Classes |
The list of classes in the model
| |
Regularisation |
Neural network L-1 regularization parameter.
| |
TerminationDelegate |
The user's stop criterion function.
| |
TerminationIterations |
The maximum optimization iterations number. Zero means infinite iterations.
| |
TerminationObjectiveChange |
Objective function change stop criterion. Null means no objective change termination conditions.
| |
TerminationTimeout |
The optimization algorithm timeout: the execution will be interrupted on the next step after the timeout expiration.
| |
Topology |
The neural network model topology
| |
TrainBestIteration |
Last Train or Update operation best step index.
| |
TrainBestValue |
Last Train or Update operation best objective value.
| |
TrainTotalIterations |
Last Train or Update operation total steps number.
|
Name | Description | |
---|---|---|
Clear |
Clear model - free resources
| |
Dispose |
This code added to correctly implement the disposable pattern.
| |
Equals | Determines whether the specified object is equal to the current object. (Inherited from Object.) | |
GetHashCode | Serves as the default hash function. (Inherited from Object.) | |
GetObjectData |
The object optimized serialization method.
| |
GetType | Gets the Type of the current instance. (Inherited from Object.) | |
Load |
Load model from file.
| |
Save |
Save model to file.
| |
ToString | Returns a string that represents the current object. (Inherited from Object.) |