BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:LMSS @ Cornell Tech: Kyunghyun Cho (NYU/Facebook AI Research)
X-WR-TIMEZONE:Eastern Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260910T062647Z
UID:tag:localist.com\,2008:EventInstance_32520819009731
DTSTART:20200306T170000Z
DTEND:20200306T183000Z
DESCRIPTION:Learning Machines Seminar Series\n\nWhat: LMSS @ Cornell Tech: 
 Kyunghyun Cho (NYU/Facebook AI Research)\nWhen: Friday\, March 6th\, 12:15
  p.m. (lunch served at 12pm)\nWhere: Room 061\, Bloomberg Center\, Cornell
  Tech (map)\n\n \n\n"Inconsistency of a recurrent language model: a questi
 on i forgot to ask in 2014"\n\nIn this talk\, I will go back to the basic 
 of neural sequence modeling and ask the glaringly obvious question I forgo
 t to ask in 2014\; "is density estimation a good strategy for sequence gen
 eration?" I try to give my initial stab at belatedly answering this questi
 on by empirically investigating the discrepancy between density estimation
  and sequence generation\, studying the effectiveness of two distinct appr
 oaches to neural sequence modeling (Lee\, Tran\, Firat & Cho\, 2020 under 
 review)\, and by theoretically studying the inconsistency of incomplete de
 coding in a recurrent language model (Welleck\, Kulikov\, Kim\, Pang & Cho
 \, 2020 under review). I will conclude the talk by discussing some lessons
  I have learned during the past half a year trying to answer this question
 .\n\n \n\nBIO\n\nKyunghyun Cho is an associate professor of computer scien
 ce and data science at New York University\, a research scientist at Faceb
 ook AI Research and a CIFAR Associate Fellow. He was a postdoctoral fellow
  at University of Montreal until summer 2015 under the supervision of Prof
 . Yoshua Bengio\, and received PhD and MSc degrees from Aalto University e
 arly 2014 under the supervision of Prof. Juha Karhunen\, Dr. Tapani Raiko 
 and Dr. Alexander Ilin. He tries his best to find a balance among machine 
 learning\, natural language processing\, and life\, but almost always fail
 s to do so.
LOCATION:Cornell Tech\, Bloomberg Center\, Room 061
SUMMARY:LMSS @ Cornell Tech: Kyunghyun Cho (NYU/Facebook AI Research)
URL;VALUE=URI:https://events.cornell.edu/event/lmss_cornell_tech_kyunghyun_
 cho_nyu
CATEGORIES:Seminar
END:VEVENT
END:VCALENDAR