BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Incoming.tv - Improving User Experience of Mobile Video through pr
 edictive prefetching - Max Ott (NICTA)
DTSTART:20140623T100000Z
DTEND:20140623T110000Z
UID:TALK53090@talks.cam.ac.uk
CONTACT:Eiko Yoneki
DESCRIPTION:Incoming TV is an Android App (http://bit.ly/1vt7avj) which le
 arns\nabout user's video preferences and preloads the best videos in advan
 ce\nfor a superior user experience - no spinning beach balls anymore!\n\nI
 ncoming's prefetching approach is unique as most of the (machine)\nlearnin
 g is performed on the phone leading to increased privacy\, lower\ncommunic
 ation overhead and very low backend cost - and interesting\nresearch probl
 ems in 'energy-constraint ML'.\n\nThis talk will briefly outline the overa
 ll architecture and objectives\nwhich are primarily driven by content prov
 ider which clash in\ninteresting ways with network operators objectives (m
 ainly believed\,\nand less so in reality).\n\nIncoming.TV has been downloa
 ded approx. 200\,000 times and used across\nthe world leading to a trove o
 f interesting measurements for which we\nare looking for collaborators to 
 mine.\n\nBio: Max is currently a Sr. Principal Researcher at NICTA where h
 e just\nreturned from birthing Incoming Media\, a provider of mobile video
 \nsolutions for the content industry. He is actively involved in most of\n
 Future Internet research testbeds around the world. He was a Research\nPro
 fessor at WINLAB\, Rutgers U. and the Founder of Semandex\, an early\ncont
 ent-networking company.\n\n
LOCATION:FW26\, Computer Laboratory\, William Gates Builiding
END:VEVENT
END:VCALENDAR