BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//jEvents 2.0 for Joomla//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:qkdm7i1rfi82goiqsro2eu92o0@google.com
CATEGORIES:RTportal.ru
CREATED:20170606T092329
SUMMARY:Семинар СМиГО: Tensorizing Neural Networks
LOCATION:ИППИ РАН в 615 аудитории (6 этаж)
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:Докладчик: Александр Новиков (ВШЭ)\nТема: Tensorizing Neural Networks\n\nАн
 нотация:\nConvolutional neural networks excel in image recognition tasks, b
 ut this comes at the cost of high computational and memory complexity. CNNs
  require millions of floating point operations to process an image and ther
 efore real-time applications\nneed powerful CPU or GPU devices. Moreover, t
 hese networks contain millions of trainable parameters and consume hundreds
  of megabytes of storage and memory bandwidth. Thus, CNNs are forced to use
  RAM instead of solely relying on the processor cache – orders of magnitude
  more energy efficient memory device – which increases the energy consumpti
 on even more. These reasons restrain the spread of CNNs on mobile devices. 
 I will talk about our work on tensor factorization framework to compress fu
 lly-connected and convolutional layers of CNNs. Another research direction 
 (besides compression) is to increase the size of the layers by training the
 m in the compact tensor format to increase the accuracy. \n\nFor more detai
 ls see papers \nhttps://papers.nips.cc/paper/5787-tensorizing-neural-networ
 ks\nhttps://arxiv.org/abs/1611.03214 This event was imported from: https://
 rtportal.ru/index.php/kalendar-sobytij/eventdetail/121/-/seminar-smigo-tens
 orizing-neural-networks?tmpl=component
DTSTAMP:20260812T215904Z
DTSTART;TZID=Europe/Moscow:20161122T183000
DTEND;TZID=Europe/Moscow:20161122T200000
SEQUENCE:0
TRANSP:OPAQUE
END:VEVENT
END:VCALENDAR