BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://techplay.jp//JP
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALDESC:異常検知における汎化性および適応性の課題
 について【AIセキュリティ＆プライバシーチーム】
X-WR-CALNAME:異常検知における汎化性および適応性の課題
 について【AIセキュリティ＆プライバシーチーム】
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:982190@techplay.jp
SUMMARY:異常検知における汎化性および適応性の課題につ
 いて【AIセキュリティ＆プライバシーチーム】
DTSTART;TZID=Asia/Tokyo:20250716T130000
DTEND;TZID=Asia/Tokyo:20250716T140000
DTSTAMP:20260511T051257Z
CREATED:20250610T060146Z
DESCRIPTION:イベント詳細はこちら\nhttps://techplay.jp/event/98219
 0?utm_medium=referral&utm_source=ics&utm_campaign=ics\n\n\n\nAbstract\n\n
 Anomaly detection is a critical task for ensuring the reliability\, safet
 y\, and security of machine learning applications. Despite significant pr
 ogress in this area\, several key challenges remain unresolved—particul
 arly in terms of generalization\, adaptability to new datasets\, and univ
 ersality across domains. In this talk\, I will explore these ongoing chal
 lenges and present our proposed solutions aimed at addressing them. Our a
 pproach focuses on enhancing robustness and reliability in anomaly detect
 ion systems\, with the goal of improving their practical deployment in di
 verse real-world scenarios.\n\n\n\nBio\n\nMohammad Sabokrou is a Staff Re
 search Scientist at the Machine Learning and Data Science (MLDS) Unit of 
 the Okinawa Institute of Science and Technology (OIST). His research sits
  at the intersection of computer vision and trustworthy AI\, with a focus
  on anomaly and out-of-distribution detection\, continual learning\, and 
 machine learning robustness. Before OIST\, he held academic positions at 
 the Institute for Research in Fundamental Sciences (IPM) in Tehran and co
 nducted postdoctoral research at institutions across Finland and France. 
 He regularly contributes to top-tier ML conferences (e.g.\, CVPR\, ICLR\,
  NeurIPS) and serves as an area chair at ICLR 2025.
LOCATION:オンライン
URL:https://techplay.jp/event/982190?utm_medium=referral&utm_source=ics&utm
 _campaign=ics
END:VEVENT
END:VCALENDAR