BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pycon-sweden-2021//speaker//BGHKFS
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
BEGIN:DAYLIGHT
DTSTART:20201022T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20201025T030000
RDATE:20211031T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20210328T030000
RDATE:20220327T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:Zero To Hero Tutorial on a Deep Learning Classification Task - Geo
 rgios Deligiorgis\, Marco Trincavelli\, David Andersson
DTSTART;TZID=Europe/Stockholm:20211022T140000
DTEND;TZID=Europe/Stockholm:20211022T153000
DTSTAMP:20260815T014156Z
UID:pretalx-pycon-sweden-2021-993BDA@pretalx.com
DESCRIPTION:Live Stream: https://youtu.be/gnFzZRkQZ2c\n\nThis workshop wil
 l demonstrate a zero-to-hero tutorial on how to solve a classification tas
 k using deep learning. The tutorial kicks off demonstrating a simple class
 ification task on synthetic data\, first in low and then in high dimension
 . Then\, a harder classification task based on FashinMNIST\, a famous data
 set containing images of clothes\, will be tackled. Apart from solving the
  classification task itself\, we will show how to generate and analyze emb
 edding vectors that can be used to solve other downstream tasks\, differen
 t from the original classification problem on which the model was trained.
  Finally\, we are going to face a more advanced type of classification pro
 blem\, namely\, predicting links on a graph using Graph Neural Networks. L
 ink prediction will be demonstrated on an open source dataset that contain
 s information about collaborations among authors of scientific papers. The
  target of this workshop is to show how we can use Python to solve the the
  aforementioned tasks\, taking into account both the data science aspects 
 and the engineering and project lifecycle related ones. In particular\, th
 e python packages that we are going to cover in the workshop are PyTorch\,
  PyTorch-Lightning\, Deep Graph Library.
LOCATION:Workshops
URL:https://pretalx.com/pycon-sweden-2021/talk/993BDA/
END:VEVENT
END:VCALENDAR