BaseAveragedStochasticGradientDescentTModel, TKernel, TInput, TLoss Class

Base class for Averaged Stochastic Gradient Descent algorithm implementations.

Inheritance Hierarchy

SystemObject
  Accord.MachineLearningBinaryLearningBaseTModel, TInput
    Accord.MachineLearning.VectorMachines.LearningBaseAveragedStochasticGradientDescentTModel, TKernel, TInput, TLoss
      Accord.MachineLearning.VectorMachines.LearningAveragedStochasticGradientDescent
      Accord.MachineLearning.VectorMachines.LearningAveragedStochasticGradientDescentTKernel
      Accord.MachineLearning.VectorMachines.LearningAveragedStochasticGradientDescentTKernel, TInput
      Accord.MachineLearning.VectorMachines.LearningAveragedStochasticGradientDescentTKernel, TInput, TLoss

Namespace: Accord.MachineLearning.VectorMachines.Learning
Assembly: Accord.MachineLearning (in Accord.MachineLearning.dll) Version: 3.8.0

Syntax

Copy

public abstract class BaseAveragedStochasticGradientDescent<TModel, TKernel, TInput, TLoss> : BinaryLearningBase<TModel, TInput>, 
	ICloneable
where TModel : SupportVectorMachine<TKernel, TInput>
where TKernel : struct, new(), ILinear<TInput>
where TInput : IList, ICloneable
where TLoss : struct, new(), IDifferentiableLoss<bool, double, double>

Public MustInherit Class BaseAveragedStochasticGradientDescent(Of TModel As SupportVectorMachine(Of TKernel, TInput), TKernel As {Structure, New, ILinear(Of TInput)}, TInput As {IList, ICloneable}, TLoss As {Structure, New, IDifferentiableLoss(Of Boolean, Double, Double)})
	Inherits BinaryLearningBase(Of TModel, TInput)
	Implements ICloneable

Request Example View Source

Type Parameters

TModel: The type of the model being learned.
TKernel: The type of the kernel function to use.
TInput: The type of the input to consider.
TLoss: The type of the loss function to use.

The BaseAveragedStochasticGradientDescentTModel, TKernel, TInput, TLoss type exposes the following members.

Constructors

	Name	Description
	BaseAveragedStochasticGradientDescentTModel, TKernel, TInput, TLoss	Initializes a new instance of the BaseAveragedStochasticGradientDescentTModel, TKernel, TInput, TLoss class.

Top

Properties

	Name	Description
	CurrentEpoch	Gets or sets the current epoch counter.
	Iterations	Obsolete. Please use MaxIterations instead.
	Kernel	Gets or sets the kernel function use to create a kernel Support Vector Machine.
	Lambda	Gets or sets the lambda regularization term. Default is 0.5.
	LearningRate	Gets or sets the learning rate for the SGD algorithm.
	Loss	Gets or sets the loss function to be used. Default is to use the LogisticLoss.
	MaxIterations	Gets or sets the number of iterations that should be performed by the algorithm when calling Learn(TInput, Boolean, Double). Default is 0 (iterate until convergence).
	Model	Gets or sets the classifier being learned. (Inherited from BinaryLearningBaseTModel, TInput.)
	ParallelOptions	Gets or sets the parallelization options for this algorithm.
	Token	Gets or sets a cancellation token that can be used to cancel the algorithm while it is running. (Overrides BinaryLearningBaseTModel, TInputToken.)
	Tolerance	Gets or sets the maximum relative change in the watched value after an iteration of the algorithm used to detect convergence. Default is 1e-3. If set to 0, the loss will not be computed during learning and execution will be faster.

Top

Methods

	Name	Description
	Clone	Creates a new object that is a copy of the current instance.
	Create	Creates an instance of the model to be learned. Inheritors of this abstract class must define this method so new models can be created from the training data.
	Equals	Determines whether the specified object is equal to the current object. (Inherited from Object.)
	Finalize	Allows an object to try to free resources and perform other cleanup operations before it is reclaimed by garbage collection. (Inherited from Object.)
	GetHashCode	Serves as the default hash function. (Inherited from Object.)
	GetType	Gets the Type of the current instance. (Inherited from Object.)
	InnerClone	Inheritors should implement this function to produce a new instance with the same characteristics of the current object.
	Learn(TInput, Boolean, Double)	Learns a model that can map the given inputs to the given outputs. (Inherited from BinaryLearningBaseTModel, TInput.)
	Learn(TInput, Double, Double)	Learns a model that can map the given inputs to the given outputs. (Inherited from BinaryLearningBaseTModel, TInput.)
	Learn(TInput, Int32, Double)	Learns a model that can map the given inputs to the given outputs. (Inherited from BinaryLearningBaseTModel, TInput.)
	Learn(TInput, Int32, Double)	Learns a model that can map the given inputs to the given outputs. (Inherited from BinaryLearningBaseTModel, TInput.)
	Learn(TInput, Boolean, Double)	Learns a model that can map the given inputs to the given outputs. (Overrides BinaryLearningBaseTModel, TInputLearn(TInput, Boolean, Double).)
	MemberwiseClone	Creates a shallow copy of the current Object. (Inherited from Object.)
	ToString	Returns a string that represents the current object. (Inherited from Object.)

Top

Extension Methods

	Name	Description
	HasMethod	Checks whether an object implements a method with the given name. (Defined by ExtensionMethods.)
	IsEqual	Compares two objects for equality, performing an elementwise comparison if the elements are vectors or matrices. (Defined by Matrix.)
	To(Type)	Overloaded. Converts an object into another type, irrespective of whether the conversion can be done at compile time or not. This can be used to convert generic types to numeric types during runtime. (Defined by ExtensionMethods.)
	ToT	Overloaded. Converts an object into another type, irrespective of whether the conversion can be done at compile time or not. This can be used to convert generic types to numeric types during runtime. (Defined by ExtensionMethods.)

Top

Remarks

The IKernel and IDifferentiableLossTInput, TScore, TLoss are passed as generic parameters (constrained to be structs) because this is the only way to force the compiler to emit a separate native code for this class whose performance critical sections can be inlined.

Reference

Accord.MachineLearning.VectorMachines.Learning Namespace

Accord.MachineLearning.VectorMachines.LearningStochasticGradientDescent

Accord.MachineLearning.VectorMachines.LearningAveragedStochasticGradientDescent

Accord.MachineLearningBinaryLearningBaseTModel, TInput

BaseAveragedStochasticGradientDescentAddLanguageSpecificTextSet("LST786FD39E_0?cs=&lt;|vb=(Of |cpp=&lt;|fs=&lt;'|nu=(");TModel, TKernel, TInput, TLossAddLanguageSpecificTextSet("LST786FD39E_1?cs=&gt;|vb=)|cpp=&gt;|fs=&gt;|nu=)"); Class

Type Parameters

Reference

BaseAveragedStochasticGradientDescentTModel, TKernel, TInput, TLoss Class