BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:[ONLINE] Advanced Deep Learning with Transformers @ENCCS&RISE
DTSTART;VALUE=DATE-TIME:20211021T070000Z
DTEND;VALUE=DATE-TIME:20211021T103000Z
DTSTAMP;VALUE=DATE-TIME:20211128T165646Z
UID:indico-event-1260@events.prace-ri.eu
DESCRIPTION:Overview\n\nIn recent years\, Graph Neural Networks (GNNs) a
nd Transformers have led to numerous break-through achievements in a var
iety of fields such as Natural Language Processing (NLP)\, chemistry and p
hysics. By doing away with the need for fixed-size inputs\, these architec
tures significantly extend the scope of problems in which deep learning ca
n be applied.\nPreliminary Agenda\n\nThis workshop will take you from the
representation of graphs and finite sets as inputs for neural networks to
the implementation of full GNNs for a variety of tasks. You will learn abo
ut the central concepts used in GNNs in a hands-on setting using Jupyter N
otebooks and a series of coding exercises. While the workshop will use pro
blems from the field of chemistry as an example for applications\, the ski
lls you learn can be transferred to any domain where finite set or graph-b
ased representations of data are appropriate. From GNNs\, we will make the
leap to Transformer architectures\, and explain the conceptual ties betwe
en the two.\n\nThe workshop is free of charge and will be conducted full
y online using zoom.\n\nPrerequisites\n\nTo successfully participate in th
is workshop\, you should have a good understanding of basic linear algebra
and core concepts of deep learning such as CNNs\, stochastic gradient des
cent\, and supervised learning. You should also be familiar with the imple
mentation of neural networks using PyTorch. A basic conceptual understandi
ng of mathematical graphs is recommended but not a prerequisite.\n\nAgenda
\n\nFor updated agenda you can follow this link\nhttps://enccs.se/events/2
021/10/advanced-deep-learning/\n\nContact person\n\nApostolos Vasileiadis
apostolos.vasileiadis@it.uu.se\n\nhttps://events.prace-ri.eu/event/1260/
LOCATION:Online
URL:https://events.prace-ri.eu/event/1260/
END:VEVENT
END:VCALENDAR