News for hackers. Stuff that matters.
Re:Model-Based Machine Learning by highd on Sunday December 04, 2016 @08:33PM (#13102814)
One of the most popular ways of using techniques like this is the "Variational Autoencoder". I've been working on using some alternate distributions with them as of late - it's very interesting, and quite powerful.
Re:Model-Based Machine Learning by nl on Monday December 05, 2016 @06:27AM (#13104749)
How does this work? You use the VAE to model variables and then somehow get the distribution from them?

Got a link? (I know the basics of VAEs, but I'm missing how to link them to this)

Re:Model-Based Machine Learning by highd on Monday December 05, 2016 @01:33PM (#13107902)
The VAE "coder" is modelling a distribution p(z|x), and the decoder is modelling a distribution p(x|z).

I like these slides: https://home.zhaw.ch/~dueo/bbs/files/vae.pdf