Prelaunch – Probabilistic Programming Primer

beaker-700x438
How I used to feel when people mentioned PyMC3/MCMC/Probabilistic Programming

I’m excited to announce the pre-launch of a new project, that I’ve been spending some time thinking about.

I’m a core developer of PyMC3 – and that isn’t as impressive as it sounds 🙂 I’m honoured to work with smart people and learn a lot about Probabilistic Programming from it. However it doesn’t mean I know everything. The literature is still quite difficult to grok, and the aim of this project is to make it easier for experienced ML engineers, analysts, programmers etc to be able to adopt these techniques.

pymctraces_1600x990.png
The kind of diagram you’ll learn how to understand from my course – source Jon Sedar

Most of my material will be based on notes and conference submissions from the last few years – however it will include my own insights, it’ll all be in one place and it’ll help you get to grips with Bayesian Stats.

Roughly the syllabus will be:

– What PyMC3 is for
– What MCMC is and why should I care
– How to know enough theano to not be scared by it
– How to diagnose things like model convergence and figure out if your model is good or not
– An introduction to Multi-level models or Bayesian Stats super sauce

If you’re interested get over to https://probabilisticprogrammingprimer.podia.com/ and sign up to the pre-launch list!

Also feel free to ping me on Twitter if there are any particular topics you’d like to see featured in my course that I’m not covering so far.

Leave a Reply