Skip to content

dingchenwei/Likelihood-free_OICA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Likelihood-Free OICA

Existing OICA algorithms usually make strong parametric assumptions on the distribution of independent components, which may be violated on real data, leading to sub-optimal or even wrong solutions.

Likelihood-Free Overcomplete ICA algorithm (LFOICA) estimates the mixing matrix directly by backpropagation without any explicit assumptions on the density function of independent components. It first transform random noise into components, then use a generation process that mimic the mixing procedure that mix components into mixtures. MMD between the observed mixtures and estimated mixtures is used as a teacher to guide the mixing matrix and components learning process.

Required python packages

pytorch

numpy

Usage

python LFOICA.py --num_components --num_mixtures --cuda(if applicable)

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages