BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconde-pydata-berlin-2023//talk//3TH9UC
BEGIN:VTIMEZONE
TZID:Europe/Berlin
BEGIN:DAYLIGHT
DTSTART:20220419T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20221030T030000
RDATE:20231029T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20230326T030000
RDATE:20240331T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Teaching Neural Networks a Sense of Geometry - Jens Agerberg
DTSTART;TZID=Europe/Berlin:20230419T105000
DTEND;TZID=Europe/Berlin:20230419T112000
DTSTAMP:20260811T182023Z
UID:pretalx-pyconde-pydata-berlin-2023-3TH9UC@pretalx.com
DESCRIPTION:By taking neural networks back to the school bench and teachin
 g them some elements of geometry and topology we can build algorithms that
  can reason about the shape of data. Surprisingly these methods can be use
 ful not only for computer vision – to model input data such as images or
  point clouds through global\, robust properties – but in a wide range o
 f applications\, such as evaluating and improving the learning of embeddin
 gs\, or the distribution of samples originating from generative models. Th
 is is the promise of the emerging field of Topological Data Analysis (TDA)
  which we will introduce and review recent works at its intersection with 
 machine learning. TDA can be seen as being part of the increasingly popula
 r movement of Geometric Deep Learning which encourages us to go beyond see
 ing data only as vectors in Euclidean spaces and instead consider machine 
 learning 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.
LOCATION:B05-B06
URL:https://pretalx.com/pyconde-pydata-berlin-2023/talk/3TH9UC/
END:VEVENT
END:VCALENDAR