University of Cambridge > > Machine Learning @ CUED > Computable Probability Theory

Computable Probability Theory

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Zoubin Ghahramani.

How much of statistics can we automate? At MIT , I’m working as a member of a team to develop a probabilistic programming language, Church, suitable for rigorously and formally specifying probabilistic models and a language implementation, MIT -Church, capable of performing automatic inference. In this talk, I’ll discuss some of the theoretical limits of this endeavor, in particular work concerning universality, representational equivalence, and computability of conditioning. I might even wax philosophical on the last point.

This is joint work with Nate Ackerman (UPenn) and Cameron Freer (MIT).

This talk is part of the Machine Learning @ CUED series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity