BEGIN:VCALENDAR
VERSION:2.0
PRODID:OpenCms 21.0.11
BEGIN:VTIMEZONE
TZID:Europe/Berlin
X-LIC-LOCATION:Europe/Berlin
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700329T020000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701025T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
END:STANDARD
END:VTIMEZONE				
BEGIN:VEVENT
DTSTAMP:20191220T122648
UID:9c4de0c3-231b-11ea-855e-000e0c3db68b
SUMMARY:Vortrag von Prof. Marc Niethammer
DESCRIPTION:Prof. Marc Niethammer\nDepartment of Computer Science\nThe University of North Carolina at Chapel Hill  \nMonday 2021-07-05 16:00\nWebex Meeting  \nAbstract\nImage registration is an important component for many medical image analysis methods to\nestablish spatial correspondences. Over the last years many deep learning approaches to image\nregistration have been proposed. In this talk, I will give a brief overview of how these deep\nlearning approaches go beyond more classical optimization-based registration approaches and how\nthey allow for more sophisticated formulations. In particular, I will emphasize how these\napproaches motivate significantly simpler registration formulations and how they can motivate a\ndifferent way of parameterizing deep neural networks.  \nBiographical Information\nMarc Niethammer is a Professor at the University of North Carolina at Chapel Hill in the\nDepartment of Computer Science. He received his Ph.D. in Electrical and Computer Engineering from\nthe Georgia Institute of Technology and post-doctoral training at Harvard Medical School/Brigham\nand Women's Hospital. His research interests lie in the areas of biomedical image analysis focusing\non application-driven algorithm design for segmentation, registration, machine learning, and shape\nanalysis.  \nClick \nhere to join the Webex Meeting 
DTSTART;TZID=Europe/Berlin;VALUE=DATE:20210705
URL;VALUE=URI:https://www.ist.uni-stuttgart.de/de/veranstaltungen/Vortrag-von-Prof.-Marc-Niethammer/
END:VEVENT
END:VCALENDAR