Flow-based generative model: Difference between revisions

Revision as of 07:19, 11 March 2021

Revision as of 07:24, 11 March 2021

Line 3:

{{Machine learning bar}}

A '''flow-based generative model''' is a [[generative model]] that explicitly models the [[probability density function]] of the real data (i.e. <math>p(\textbf{x})</math>). This is accomplished by leveraging the [[Probability density function#Function of random variables and change of variables in the probability density function|change-of-variables]] law of probabilities to transform a simple distribution into a complex ones.

== Implementations ==

TODO description

* RealNVP

* TODO more items, and citation

== Applications ==

TODO description

* Point-cloud modeling

* Music generation

* TODO more items, and citation

== References ==

Line 10 ⟶ 25:

{{reflist}}

== External links ==

TODO

[[Category:Machine learning]]