BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Sabre//Sabre VObject 4.6.0//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Zurich
X-LIC-LOCATION:Europe/Zurich
TZURL:http://tzurl.org/zoneinfo/Europe/Zurich
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19810329T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19961027T030000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:news2582@europa.unibas.ch
DTSTAMP;TZID=Europe/Zurich:20241010T071837
DTSTART;TZID=Europe/Zurich:20241104T140000
SUMMARY:RISE Crash Course: «Information Extraction from Images with AI»
DESCRIPTION:In this two-hour\, hybrid course\, you will learn how multimoda
 l large language models\, such as ChatGPT-4o\, Gemini 1.5\, or Claude Sonn
 et 3.5\, can be used to extract structured information directly from image
 s. This approach eliminates the often necessary intermediate step of text 
 recognition and transcription that is common in traditional methods (such 
 as Transkribus).\\r\\nUsing concrete examples from ongoing research projec
 ts\, the course will demonstrate the practical possibilities and limitatio
 ns of this technology. It will also address the technical and methodologic
 al prerequisites required for successful implementation. Additionally\, as
 pects of data quality\, the FAIRness (Findability\, Accessibility\, Intero
 perability\, Reusability) of the extracted data\, as well as the associate
 d costs\, will be considered and reflected upon.\\r\\nThe course is aimed 
 at researchers and students in the social sciences and humanities. The num
 ber of participants is limited to 15 people (on-site) per session. If need
 ed\, the course can be offered in English. Questions and contributions in 
 English are\, of course\, always welcome regardless of the course language
 . \\r\\nPlaces will be allocated on a first-come\, first-served basis. Re
 gister now [https://docs.google.com/forms/d/e/1FAIpQLSfVGuXqWjFigq8x9miM4M
 hqL3V1MEkjm5nEu-UJXYEUT3ofig/viewform?usp=sf_link].
X-ALT-DESC:<p>In this two-hour\, hybrid course\, you will learn how multimo
 dal large language models\, such as ChatGPT-4o\, Gemini 1.5\, or Claude So
 nnet 3.5\, can be used to extract structured information directly from ima
 ges. This approach eliminates the often necessary intermediate step of tex
 t recognition and transcription that is common in traditional methods (suc
 h as <a href="https://rise.unibas.ch/en/event/details/rise-crash-course-tr
 anskribus/" target="_blank"><u>Transkribus</u></a>).</p>\n<p>Using concret
 e examples from ongoing research projects\, the course will demonstrate th
 e practical possibilities and limitations of this technology. It will also
  address the technical and methodological prerequisites required for succe
 ssful implementation. Additionally\, aspects of data quality\, the FAIRnes
 s (Findability\, Accessibility\, Interoperability\, Reusability) of the ex
 tracted data\, as well as the associated costs\, will be considered and re
 flected upon.</p>\n<p>The course is aimed at researchers and students in t
 he social sciences and humanities. The number of participants is limited t
 o 15 people (on-site) per session. If needed\, the course can be offered i
 n English. Questions and contributions in English are\, of course\, always
  welcome regardless of the course language.&nbsp\;</p>\n<p>Places will be 
 allocated on a first-come\, first-served basis. <a href="https://docs.goog
 le.com/forms/d/e/1FAIpQLSfVGuXqWjFigq8x9miM4MhqL3V1MEkjm5nEu-UJXYEUT3ofig/
 viewform?usp=sf_link" target="_blank">Register now</a>.</p>
DTEND;TZID=Europe/Zurich:20241104T160000
END:VEVENT
END:VCALENDAR