BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//UM//UM*Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:America/Detroit
TZURL:http://tzurl.org/zoneinfo/America/Detroit
X-LIC-LOCATION:America/Detroit
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20070311T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20071104T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260903T145703
DTSTART;TZID=America/Detroit:20261001T160000
DTEND;TZID=America/Detroit:20261001T170000
SUMMARY:Workshop / Seminar:Enhancing biological datasets using artificial intelligence
DESCRIPTION:Seminar summary - Biological data have expanded in breadth and depth over the last decade\, leading to larger datasets that hold the potential to answer questions at greater resolution. Despite this growth\, some datasets remain inherently limited\; including many derived from specimens from natural history collections. In this talk\, Bryan Carstens will discuss the potential of Artificial Intelligence approaches to improve biological datasets. One example describes the application of transfer learning to improve the genomic data collected from specimens where the sampling is inherently limited\, such as from extinct species. A second describes the use of neutral networks to automate pseudo-landmarks in three dimensional geometric morphometrics. Taken together\, this work suggests that AI has the potential to enhance biological data\, leading to increased inferential capabilities.
UID:151542-21911709@events.umich.edu
URL:https://events.umich.edu/event/151542
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Ecology And Evolutionary Biology,eeb,Environment,Lecture,Research,seminar,Workshop
LOCATION:Biological Sciences Building - 1060
CONTACT:
END:VEVENT
END:VCALENDAR