BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Machine Learning for high-energy physics and the Higgs ML challeng
 e - Gabor Melis and Tim Salimans
DTSTART:20141114T160000Z
DTEND:20141114T170000Z
UID:TALK54478@talks.cam.ac.uk
CONTACT:Damien George
DESCRIPTION:High Energy Physics provides a challenging data domain with da
 ta that is\nhighly structured\, but also very noisy.  Salimans will presen
 t what he has learned\nanalysing such data for the Higgs ML challenge\, fo
 cusing on methods that are\nable to effectively search through a high dime
 nsional model space while\nalso achieving good statistical efficiency.  In
  addition\, he will discuss the\nrole of the physicist in modelling this t
 ype of data\, and talk about robustly\napplying the findings to real (not 
 simulated) HEP data.\nMelis will describe the winning solution of the Higg
 s ML challenge\, the issues\nrelated to the evaluation metric and reliable
  assessment of model\nperformance. He will take a stab at predicting how t
 o achieve larger improvements.\n[This is a joint presentation.]
LOCATION:MR19 (Potter Room\, Pavilion B)\, CMS
END:VEVENT
END:VCALENDAR