BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTAMP:20260703T180242Z
UID:8ac35791-ceee-4571-9a96-bd5e3a806d09
DTSTART:20211021T070000Z
DTEND:20211021T103000Z
DESCRIPTION:Overview\n\nIn recent years\, Graph Neural Networks (GNNs) an
 d Transformers have led to numerous break-through achievements in a vari
 ety of fields such as Natural Language Processing (NLP)\, chemistry and ph
 ysics. By doing away with the need for fixed-size inputs\, these architect
 ures significantly extend the scope of problems in which deep learning can
  be applied.\nPreliminary Agenda\n\nThis workshop will take you from the r
 epresentation of graphs and finite sets as inputs for neural networks to t
 he implementation of full GNNs for a variety of tasks. You will learn abou
 t the central concepts used in GNNs in a hands-on setting using Jupyter No
 tebooks and a series of coding exercises. While the workshop will use prob
 lems from the field of chemistry as an example for applications\, the skil
 ls you learn can be transferred to any domain where finite set or graph-ba
 sed representations of data are appropriate. From GNNs\, we will make the 
 leap to Transformer architectures\, and explain the conceptual ties betwee
 n the two.\n\nThe workshop is free of charge and will be conducted fully
  online using zoom.\n\nPrerequisites\n\nTo successfully participate in thi
 s workshop\, you should have a good understanding of basic linear algebra 
 and core concepts of deep learning such as CNNs\, stochastic gradient desc
 ent\, and supervised learning. You should also be familiar with the implem
 entation of neural networks using PyTorch. A basic conceptual understandin
 g of mathematical graphs is recommended but not a prerequisite.\n\nAgenda\
 n\nFor updated agenda you can follow this link\nhttps://enccs.se/events/20
 21/10/advanced-deep-learning/\n\nContact person\n\nApostolos Vasileiadis a
 postolos.vasileiadis@it.uu.se\nhttps://events.prace-ri.eu/event/1260/
SUMMARY:[ONLINE] Advanced Deep Learning with Transformers @ENCCS&RISE
URL;VALUE=URI:https://events.prace-ri.eu/event/1260/
END:VEVENT
END:VCALENDAR