BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Liquid State Theory Meets Deep Learning and Molecular Informatics 
 - Alpha Lee\, Cavendish Laboratory
DTSTART:20180306T130000Z
DTEND:20180306T140000Z
UID:TALK97786@talks.cam.ac.uk
CONTACT:Professor Mike Cates
DESCRIPTION:A large class of problems in machine learning pertains to maki
 ng sense of high dimensional and unlabelled data. The challenge lies in se
 parating direct variable-variable interactions (e.g. cause and effect) and
  transitive correlations\, as well as removing noise due to insufficient n
 umber of samples relative to the number of variables. In this talk\, I wil
 l discuss an Ornstein-Zernike-like approach for data analysis that disenta
 ngles correlations in datasets using ideas from the theory of liquids. The
  Ornstein-Zernike closure is parameterised by deep learning\, and a framew
 ork inspired by random matrix theory is used to remove finite sampling noi
 se. I will illustrate this approach by applying it to problems such as lig
 and-based virtual screening and predicting protein function from sequence 
 covariation.  
LOCATION:MR11\, CMS
END:VEVENT
END:VCALENDAR