Skip to content

dusenberrymw/mixture-density-networks

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 

Repository files navigation

Mixture Density Networks

An exploration of mixture density networks.

Background

A mixture density network (MDN) is an interesting model formalism built within the general framework of neural networks and probability theory for working on supervised learning problems in which the target variable cannot be easily approximated by a single standard probability distribution. Essentially, an MDN allows one to model a conditional probability distribution p(y|x) as a mixture of distributions, in which the individual distributions and the corresponding mixture coefficients are parameterized by functions of the inputs x.

Notebook

Blog post

Resources

  1. Pattern Recognition and Machine Learning (PRML), pp. 272-277, pp. 430-435
  2. @hardmaru's MDN blogs: http://blog.otoro.net/2015/06/14/mixture-density-networks, http://blog.otoro.net/2015/11/24/mixture-density-networks-with-tensorflow
  3. http://edwardlib.org/tutorials/mixture-density-network

About

An exploration of mixture density networks

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published