DeepNeuralNetwork Class

The deep neural network model

Inheritance Hierarchy

Namespace: FinMath.MachineLearning.NeuralNetworks
Assembly: FinMath (in FinMath.dll) Version: 2.4.7-0a995bd0ea1854c2c868ec3f8dae606c5777e170

Syntax

[SerializableAttribute]
public class DeepNeuralNetwork : FFNetClassifier, 
	IBaseClassifier

The DeepNeuralNetwork type exposes the following members.

Constructors

	Name	Description
	DeepNeuralNetwork	Default constructor
	DeepNeuralNetwork(SerializationInfo, StreamingContext)	The object deserialization constructor.

Properties

	Name	Description
	Classes	The list of classes in the model (Inherited from FFNet.)
	CustomLoss	External loss function. (Inherited from FFNetClassifier.)
	Regularisation	Neural network L-1 regularization parameter. (Inherited from FFNet.)
	TerminationDelegate	The user's stop criterion function. (Inherited from FFNet.)
	TerminationIterations	The maximum optimization iterations number. Zero means infinite iterations. (Inherited from FFNet.)
	TerminationObjectiveChange	Objective function change stop criterion. Null means no objective change termination conditions. (Inherited from FFNet.)
	TerminationTimeout	The optimization algorithm timeout: the execution will be interrupted on the next step after the timeout expiration. (Inherited from FFNet.)
	Topology	The neural network model topology (Inherited from FFNet.)
	TrainBestIteration	Last Train or Update operation best step index. (Inherited from FFNet.)
	TrainBestValue	Last Train or Update operation best objective value. (Inherited from FFNet.)
	TrainTotalIterations	Last Train or Update operation total steps number. (Inherited from FFNet.)

Methods

	Name	Description
	Classify(Matrix)	Classifies the observation matrix. (Inherited from FFNetClassifier.)
	Classify(Vector)	Classifies the observation vector. (Inherited from FFNetClassifier.)
	Classify(Matrix, IntegerArray)	Classifies the observation matrix. (Inherited from FFNetClassifier.)
	Clear	Clear model - free resources (Inherited from FFNet.)
	Dispose	This code added to correctly implement the disposable pattern. (Inherited from FFNet.)
	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. (Inherited from FFNet.)
	GetType	Gets the Type of the current instance. (Inherited from Object.)
	Load	Load model from file. (Inherited from FFNet.)
	Save	Save model to file. (Inherited from FFNet.)
	ToString	Returns a string that represents the current object. (Inherited from Object.)
	Train(Matrix, IntegerArray)	Train classifier (default version).
	Train(Matrix, IntegerArray, Int32)	Train classifier.
	Update	Update model weights with new observations (Inherited from FFNetClassifier.)