HLearn-distributions-0.0.1.2: Distributions for use with the HLearn library

HLearn.Models.Distributions.Gaussian

Description

The Gaussian distribution is an instance of 'HomTrainer.' For examples of how to use this type, and the math behind it, see: http://izbicki.me/blog/gausian-distributions-are-monoids.

Synopsis

# Documentation

data Gaussian datapoint Source

Constructors

 Gaussian Fieldsn :: !IntThe number of samples trained on m1 :: !datapointThe mean (first moment) of the trained distribution m2 :: !datapointThe variance (second moment) of the trained distribution times (n-1) dc :: !IntThe number of "dummy points" that have been added to the distribution. Required for numerical stability reasons.

Instances

 (MVector (Mutable Vector) (Gaussian a0), Unbox a0) => Vector Vector (Gaussian a0) Unbox a0 => MVector MVector (Gaussian a0) HomTrainer GaussianPDFParams (Gaussian Double) GaussianPDF Read datapoint => Read (Gaussian datapoint) Show datapoint => Show (Gaussian datapoint) NFData datapoint => NFData (Gaussian datapoint) Fractional datapoint => Semigroup (Gaussian datapoint) Fractional datapoint => Monoid (Gaussian datapoint) (Semigroup (Gaussian datapoint), Fractional datapoint) => RegularSemigroup (Gaussian datapoint) (RegularSemigroup (Gaussian datapoint), Monoid (Gaussian datapoint), Fractional datapoint) => Group (Gaussian datapoint) (Vector Vector (Gaussian a0), MVector MVector (Gaussian a0), Unbox a0) => Unbox (Gaussian a0) Distribution (Gaussian Double) Double Double HomTrainer (GaussianParams Double) Double (Gaussian Double) Model (GaussianParams datatype) (Gaussian datatype) Model (GaussianParams datatype) (Gaussian datatype) => DefaultModel (GaussianParams datatype) (Gaussian datatype)

data GaussianParams datatype Source

Training a Gaussian distribution takes no parameters

Constructors

 GaussianParams

Instances

 NFData (GaussianParams datatype) HomTrainer (GaussianParams Double) Double (Gaussian Double) Model (GaussianParams datatype) (Gaussian datatype) Model (GaussianParams datatype) (Gaussian datatype) => DefaultModel (GaussianParams datatype) (Gaussian datatype)