Click or drag to resize
Accord.NET (logo)

GaussianMixtureModelOptions Properties

The GaussianMixtureModelOptions type exposes the following members.

Public propertyIterations
Gets or sets the maximum number of iterations to be performed by the Expectation-Maximization algorithm. Default is zero (iterate until convergence).
Public propertyLogarithm
Gets or sets whether to make computations using the log -domain. This might improve accuracy on large datasets.
Public propertyNormalOptions
Gets or sets the fitting options for the component Gaussian distributions of the mixture model.
Public propertyParallelOptions
Gets or sets parallelization options.
Public propertyThreshold
Gets or sets the convergence criterion for the Expectation-Maximization algorithm. Default is 1e-3.
Public propertyWeights
Gets or sets the sample weights. If set to null, the data will be assumed equal weights. Default is null.
See Also