BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://techplay.jp//JP
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALDESC:Talk by Dr. Pedram Ghamisi: Bridging the Gap between Earth Obs
 ervation and Machine Learning: Do We Really Need Deep Learning for Earth 
 Observation?
X-WR-CALNAME:Talk by Dr. Pedram Ghamisi: Bridging the Gap between Earth Obs
 ervation and Machine Learning: Do We Really Need Deep Learning for Earth 
 Observation?
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:744780@techplay.jp
SUMMARY:Talk by Dr. Pedram Ghamisi: Bridging the Gap between Earth Observat
 ion and Machine Learning: Do We Really Need Deep Learning for Earth Obser
 vation?
DTSTART;TZID=Asia/Tokyo:20190807T110000
DTEND;TZID=Asia/Tokyo:20190807T120000
DTSTAMP:20260425T201759Z
CREATED:20190805T210007Z
DESCRIPTION:イベント詳細はこちら\nhttps://techplay.jp/event/74478
 0?utm_medium=referral&utm_source=ics&utm_campaign=ics\n\nSpeaker: Dr. Ped
 ram Ghamisi is the head of the Machine Learning group at Helmholtz-Zentru
 m Dresden-Rossendorf\, Helmholtz Institute Freiberg for Resource Technolo
 gy\, Freiberg\, Germany\, and the CTO and co-founder of VasoGnosis Inc\, 
 Milwaukee\, WI\, USA.\n\nTitle: Bridging the Gap between Earth Observatio
 n and Machine Learning: Do We Really Need Deep Learning for Earth Observa
 tion?\n\nAbstract: The field of remote sensing\, or Earth observation\, p
 rovides the possibility to map objects or areas of the Earth from a dista
 nce\, typically from aircraft or satellites. We are now facing an entirel
 y different scale of the challenge in image interpretation because of the
  enormous volume and variety of data being generated by Earth observation
  missions (e.g.\, multispectral\, hyperspectral\, RADAR\, passive microwa
 ve\, thermal\, and LiDAR). As a consequence\, the number of data produced
  by sensing devices has increased exponentially in the last few decades\,
  creating the “Big Data” phenomenon\, and leading to the creation of 
 the new field of “data science”\, including the popularization of “
 machine learning” and “deep learning” algorithms to deal with such 
 data. In contrast with machine learning which is a well-established and e
 ver-growing field of research in the remote sensing community\, deep lear
 ning at remote sensing is a very young research topic. Although young\, a
  huge number of complex deep learning-based algorithms have been develope
 d in the remote sensing community to tackle a variety of applications suc
 h as time-series remotely-sensed data analysis\, scene classification\, a
 nd multi-sensor data fusion.\nSurprisingly\, ALL the papers\, which are r
 ecognized as “most popular” by the key journals in the remote sensing
  community (e.g.\, IEEE TGRS\, IEEE GRSM\, and IEEE GRSL)\, are on the ve
 ry topic of deep learning in remote sensing (and nothing else)! Several q
 uestions now spring to mind\, e.g.\, do we really need deep learning in r
 emote sensing or we only have a tendency toward new\, eye-catching trends
 ? How is the performance of new deep approaches compared to well-establis
 hed machine learning techniques for the analysis of remote sensing data w
 ith unique nature? This short presentation tries to answer the aforementi
 oned questions by providing several relevant examples in which deep learn
 ing plays a vital role in analyzing remotely-sensed data.\n\nMore informa
 tion about the speaker: http://pedram-ghamisi.com/
LOCATION:理化学研究所　革新知能統合研究センター コレ
 ド日本橋１５階  〒103-0027 東京都中央区日本橋1-4-1 日
 本橋一丁目三井ビルディング 15階
URL:https://techplay.jp/event/744780?utm_medium=referral&utm_source=ics&utm
 _campaign=ics
END:VEVENT
END:VCALENDAR