After that, for practical applications, Gen looks very promising. The MIT group already presented a very early prototype 2 years ago at PPAML.
But if you don't understand the fundamentals (generative process, mixture model, hierarchical models, non-parametric models, etc) you will be lost. Note v1 of Probmods was written in Church (a Scheme dialect), which has some advantages to create meta-models.
https://probmods.org/
It's my favorite book since SICP & CTM. Some auxiliary materials:
http://forestdb.org/
http://dippl.org/
https://mhtess.github.io/bdappl/
After that, for practical applications, Gen looks very promising. The MIT group already presented a very early prototype 2 years ago at PPAML.
But if you don't understand the fundamentals (generative process, mixture model, hierarchical models, non-parametric models, etc) you will be lost. Note v1 of Probmods was written in Church (a Scheme dialect), which has some advantages to create meta-models.