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:20260305T105250
DTSTART;TZID=America/Detroit:20260318T160000
DTEND;TZID=America/Detroit:20260318T170000
SUMMARY:Workshop / Seminar:Publishing (Student Success Workshops)
DESCRIPTION:Join us and the Editorial Coordinator at Michigan Publishing Services\, Dr. Marisa Mercurio\, to learn about undergraduate publishing. We will cover things such as reasons for publishing\, the publishing process\, and publishing opportunities at UM. \nRegister here: https://myumi.ch/Z2qVj
UID:141971-21889702@events.umich.edu
URL:https://events.umich.edu/event/141971
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Transfer Students,Undergraduate,Undergraduate Students,Urop,Workshop,Writing
LOCATION:Undergraduate Science Building - 1160
CONTACT:
END:VEVENT
BEGIN:VEVENT
DTSTAMP:20260315T213916
DTSTART;TZID=America/Detroit:20260318T160000
DTEND;TZID=America/Detroit:20260318T170000
SUMMARY:Workshop / Seminar:Student AIM Seminar: From the Topology of Natural Images to Topological CNNs
DESCRIPTION:What kinds of hidden shapes lie in natural images\, and what can they tell us about how neural networks learn? It turns out small patches of natural images are not arranged randomly\, but around unexpected geometric structures such as circles and the Klein bottle. Later works found closely related topological organization in the learned spatial filters of convolutional neural networks (CNN). This leads to a new kind of architecture\, called the Topological CNN\, that builds this topology into the architecture of the neural network. TCNN outperforming the traditional CNN in various tasks suggests that learning can be strengthened by exploiting the topology and latent structure of data itself.
UID:146612-21899351@events.umich.edu
URL:https://events.umich.edu/event/146612
CLASS:PUBLIC
STATUS:CONFIRMED
CATEGORIES:Applied Mathematics
LOCATION:East Hall - 3088
CONTACT:
END:VEVENT
END:VCALENDAR