[Ml-stat-talks] Fwd: [talks] Colloquium Speaker: John Langford, Friday May 6, 12:30pm

Barbara Engelhardt bee at princeton.edu
Mon May 2 16:55:18 EDT 2016


Talk of interest on Friday.

---------- Forwarded message ----------


Colloquium Speaker
John Langford, Microsoft Research
Friday, May 6, 12:30pm
Computer Science 105

How to make an Infovore

An Infovore is an information-based entity that explores the world, learns,
and applies these learnings effectively.  In essence: a form of weak AI.
We have been working on a general-purpose infovore for making decisions
using elements of contextual bandits, systems, and experts-style learning
that has now been successfully deployed at large scale.  I will discuss the
architecture of the infovore, the key results upon which it relies, and how
everything works together to enable true open-loop learning in the real
world.


_______________________________________________
talks mailing list
talks at lists.cs.princeton.edu
To edit subscription settings or remove yourself, use this link:
https://lists.cs.princeton.edu/mailman/listinfo/talks
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/ml-stat-talks/attachments/20160502/5087f060/attachment.html>


More information about the Ml-stat-talks mailing list