Published on April 13, 2018 by Google

In this episode of Coffee with a Googler, Laurence Moroney sits down with Josh Dillon. Josh works on TensorFlow, Google’s open source library for numerical computation, which is typically used in Machine Learning and AI applications. He discusses working on the Distribution API, which is based on probabilistic programming. Watch this video to find out what exactly probabilistic programming is, where the use of Distributions and Bijectors comes into play, & how you can get started. Subscribe to our channel to stay up to date with Google Developers.

Introducing TensorFlow Probability blog post → goo.gl/H3LG8y
The code lives at → goo.gl/bdwspL
Referenced paper → goo.gl/HtwJnj

Watch more Coffee with a Googler → goo.gl/5l123N
Subscribe to the Google Developers Channel → goo.gl/mQyv5L

Leave a Reply

17 Comments on "Probabilistic Machine Learning in TensorFlow"

Notify of
avatar

David Wihl
Guest
David Wihl
2 months 27 days ago

Can the Distribution library replace models built in STAN? Any examples?

Umut Isik
Guest
Umut Isik
3 months 11 hours ago

Nice!

DigitArt Media
Guest
DigitArt Media
3 months 1 day ago

Jaret Ikhe
Guest
Jaret Ikhe
3 months 2 days ago

Thank you for Great content

Sabir Shakirov
Guest
Sabir Shakirov
3 months 2 days ago

О, это же Галкин

bazoozoo
Guest
bazoozoo
3 months 1 day ago

Sabir Shakirov Your recognition model is overfitted. Too much Russian TV in training data.

Alin Gabriel
Guest
Alin Gabriel
3 months 2 days ago

fantastic video 🙂 thank you for sharing your ideas!

Michel Latch
Guest
Michel Latch
3 months 2 days ago

This rocks from a pymc user

ZEUS MYLIFE_2.0
Guest
ZEUS MYLIFE_2.0
3 months 2 days ago

Developer vs statistician

i need to drive
Guest
i need to drive
3 months 3 days ago

input -> algorithm -> out.

Rizky Adhi Prasetyo
Guest
Rizky Adhi Prasetyo
3 months 3 days ago

this is what i search for, for my research

wpDiscuz