https://statproofbook.github.io/D/gm
Definition: Generative model
Index: The Book of Statistical Proofs ▷ General Theorems ▷ Bayesian statistics ▷ Probabilistic modeling ▷ Generative model
Definition: Consider measured data \(\large y\) and some unknown latent parameters \(\large \theta\).
A statement about the distribution of \(\large y\) given \(\large \theta\) is called a \(\large generative \ model\) \(\large m\):
\(\large m: y\ ∼\ D(\theta)\),
(1) where \(\large D\) denotes an arbitrary \(\large probability\ distribution\),
and \(\large \theta\) are the \(\large parameters\) of this distribution.
Sources:
Friston et al. (2008): "Bayesian decoding of brain images"; in: NeuroImage, vol. 39, pp. 181-205; URL: https://www.sciencedirect.com/science/article/abs/pii/S1053811907007203; DOI: 10.1016/j.neuroimage.2007.08.013.
Metadata: ID: D27 | shortcut: gm | author: JoramSoch | date: 2020-03-03, 15:50.
view/edit this definition