BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards quantum algorithms for natural language processing - Will 
 Zeng\, University of Oxford
DTSTART:20150130T120000Z
DTEND:20150130T130000Z
UID:TALK55303@talks.cam.ac.uk
CONTACT:Tamara Polajnar
DESCRIPTION:Recent work has begun to demonstrate the applicability of quan
 tum computing techniques to problems in machine learning.  These include a
 lgorithms for unsupervised clustering\, restricted Boltzmann machines\, an
 d perceptrons as well as optimization algorithms that can be run on adiaba
 tic quantum computers.  This talk will introduce these recent advances as 
 well as describe how these algorithms could be especially relevant to comp
 ositional models of natural language semantics\, where there is common mat
 hematical structure. At a basic level\, quantum computers are naturally su
 ited to manipulate vectors in high dimensional tensor product spaces\, so 
 it is hoped that the introduction of such devices will provide new avenues
  for natural language processing.\n\nNo working knowledge of quantum mecha
 nics will be assumed.\n
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR