Structs
- This trait represents the traditional mixture models with an underlying probability density (as opposed to k-means or SOM). They have a soft assignment, that is, for each sample and each component the likelihood is computed that the sample belongs to the component. The alternative is that a sample can only belong to one of the compent alone.
Traits
- An additional interface for
Mixables
that can be used as latent states. These can be categorical distributions, with or without finite Dirichlet or infinite Dirichlet process priors. TheMixables
are here used not multiple components but only as one distribution of the latent states.