BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-berlin-2023//talk//3TH9UC
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconde-pydata-berlin-2023-3TH9UC@pretalx.com
DTSTART;TZID=CET:20230419T105000
DTEND;TZID=CET:20230419T112000
DESCRIPTION:By taking neural networks back to the school bench and teaching
  them some elements of geometry and topology we can build algorithms that 
 can reason about the shape of data. Surprisingly these methods can be usef
 ul not only for computer vision – to model input data such as images or 
 point clouds through global\, robust properties – but in a wide range of
  applications\, such as evaluating and improving the learning of embedding
 s\, or the distribution of samples originating from generative models. Thi
 s is the promise of the emerging field of Topological Data Analysis (TDA) 
 which we will introduce and review recent works at its intersection with m
 achine learning. TDA can be seen as being part of the increasingly popular
  movement of Geometric Deep Learning which encourages us to go beyond seei
 ng data only as vectors in Euclidean spaces and instead consider machine l
 earning algorithms that encode other geometric priors. In the past couple 
 of years TDA has started to take a step out of the academic bubble\, to a 
 large extent thanks to powerful Python libraries written as extensions to 
 scikit-learn or PyTorch.
DTSTAMP:20260416T090045Z
LOCATION:B05-B06
SUMMARY:Teaching Neural Networks a Sense of Geometry - Jens Agerberg
URL:https://pretalx.com/pyconde-pydata-berlin-2023/talk/3TH9UC/
END:VEVENT
END:VCALENDAR