Learning Conditional Distributions using Mixtures of Truncated Basis Functions

Mixtures of Truncated Basis Functions (MoTBFs) have recently been proposed for modelling univariate and joint distributions in hybrid Bayesian networks. In this paper we analyse the problem of learning conditional MoTBF distributions from data. Our approach utilizes a new technique for learning...

Fuld beskrivelse

Bibliografiske detaljer
Main Authors: Pérez-Bernabé, Inmaculada, Salmerón Cerdán, Antonio, Langseth, Helge
Format: info:eu-repo/semantics/article
Sprog:English
Udgivet: 2017
Online adgang:http://hdl.handle.net/10835/4859

Lignende værker