05-06
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.

 

Date and Time
Friday May 6, 2016 12:30pm - 1:30pm
Location
Computer Science Small Auditorium (Room 105)
Speaker
John Langford, from Microsoft Research
Host
Elad Hazan

Contributions to and/or sponsorship of any event does not constitute departmental or institutional endorsement of the specific program, speakers or views presented.

CS Talks Mailing List