Selecting the optimal number of components for a Gaussian mixture model

Selecting the optimal number of components for a Gaussian mixture model

We compare two approaches to determining the optimal number of component Gaussians to include in a Gaussian mixture model, the Akaike information criterion and the Rissanen (1989) minimum description length method.< >

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: McKenzie, P., Alder, M.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Algebra
Australia
Cost function
Gaussian distribution
Gaussian processes
Information processing
Intelligent systems
Probability density function
Probability distribution
Random variables
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:We compare two approaches to determining the optimal number of component Gaussians to include in a Gaussian mixture model, the Akaike information criterion and the Rissanen (1989) minimum description length method.< >
DOI:10.1109/ISIT.1994.394626