Click or drag to resize
Accord.NET (logo)

HiddenGradientDescentLearningT Properties

The HiddenGradientDescentLearningT generic type exposes the following members.

Public propertyCurrentIteration
Gets or sets the number of performed iterations.
Public propertyFunction (Inherited from BaseHiddenConditionalRandomFieldLearningT.)
Public propertyHasConverged
Gets or sets whether the algorithm has converged.
Public propertyIterations Obsolete.
Please use MaxIterations instead.
Public propertyLearningRate
Gets or sets the learning rate to use as the gradient descent step size. Default value is 1e-1.
Public propertyMaxIterations
Gets or sets the maximum number of iterations performed by the learning algorithm.
Public propertyModel
Gets or sets the model being trained.
(Inherited from BaseHiddenConditionalRandomFieldLearningT.)
Public propertyParallelOptions
Gets or sets the parallelization options for this algorithm.
Public propertyRegularization
Gets or sets the amount of the parameter weights which should be included in the objective function. Default is 0 (do not include regularization).
Public propertyStochastic
Public propertyToken
Gets or sets a cancellation token that can be used to stop the learning algorithm while it is running.
(Inherited from BaseHiddenConditionalRandomFieldLearningT.)
Public propertyTolerance
Gets or sets the maximum change in the average log-likelihood after an iteration of the algorithm used to detect convergence.
See Also