BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://techplay.jp//JP
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALDESC:Deep Learning Theory Team Seminar (Mr. Alex LAMB)
X-WR-CALNAME:Deep Learning Theory Team Seminar (Mr. Alex LAMB)
X-WR-TIMEZONE:Asia/Tokyo
BEGIN:VTIMEZONE
TZID:Asia/Tokyo
BEGIN:STANDARD
DTSTART:19700101T000000
TZOFFSETFROM:+0900
TZOFFSETTO:+0900
TZNAME:JST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:812190@techplay.jp
SUMMARY:Deep Learning Theory Team Seminar (Mr. Alex LAMB)
DTSTART;TZID=Asia/Tokyo:20210322T080000
DTEND;TZID=Asia/Tokyo:20210322T090000
DTSTAMP:20260520T183034Z
CREATED:20210320T140011Z
DESCRIPTION:イベント詳細はこちら\nhttps://techplay.jp/event/81219
 0?utm_medium=referral&utm_source=ics&utm_campaign=ics\n\nThis is an onlin
 e seminar. Registration is required.\nWe’ll send the instruction for at
 tending the online seminar.\n\n【Deep Learning Theory Team】\n【Date
 】2021/March/22  (Mon)\n\n【Speaker】 Mr. Alex LAMB\n\nTitle: Latent D
 ata Augmentation and Modular Structure for Improved Generalization\n\nAbs
 tract: Deep neural networks have seen dramatic improvements in performanc
 e\, with much of this improvement being driven by new architectures and t
 raining algorithms with better inductive biases.  At the same time\, the 
 future of AI is systems which run in an open-ended way which run on data 
 unlike what was seen during training and which can be drawn from a changi
 ng or adversarial distribution.  These problems also require a greater sc
 ale and time horizon for reasoning as well as consideration of a complex 
 world system with many reused structures and subsystems.  This talk will 
 survey some areas where deep networks can improve their biases as well as
  my research in this direction.  These algorithms dramatically change the
  behavior of deep networks\, yet they are highly practical and easy to us
 e\, conforming to simple interfaces that allow them to easily be dropped 
 into existing codebases.  \n\nhttps://u-tokyo-ac-jp.zoom.us/j/96489539583
 ?pwd=VzIrMVF5M0ZoWGVUV25SYzhpZjM2UT09\nミーティングID: 964 8953 958
 3\nパスコード: 568749
LOCATION:オンライン
URL:https://techplay.jp/event/812190?utm_medium=referral&utm_source=ics&utm
 _campaign=ics
END:VEVENT
END:VCALENDAR