Developing a general-purpose message-passing library
- đ¤ Speaker: Tom Minka
- đ Date & Time: Friday 28 September 2007, 17:15 - 17:55
- đ Venue: Old Library, Darwin College
Abstract
Infer.NET is a project underway at Microsoft Research to create a general-purpose software library for inference in graphical models. The project is heavily inspired by BUGS and VIBES . However, the main focus of this library is efficient execution of deterministic message-passing algorithms on large-scale models. I will describe some of the research challenges we face and how we are addressing them.
Series This talk is part of the Machine Learning and Inference (One day meeting) series.
Included in Lists
- Hanchen DaDaDash
- Inference Group Summary
- Interested Talks
- Joint Machine Learning Seminars
- Machine Learning and Inference (One day meeting)
- Old Library, Darwin College
- Required lists for MLG
Note: Ex-directory lists are not shown.
![[Talks.cam]](/static/images/talkslogosmall.gif)


Friday 28 September 2007, 17:15-17:55