BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//ZContent.net//ZapCalLib 1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
DTSTART:20200805T030000
DTEND:20200805T050000
SUMMARY;CHARSET=UTF-8:Summer Academy Session: Hybrid Modelling and Theory-D
 riven Data Science
URL:https://www.sfg.at/e/summer-academy-session-hybrid-modelling-and-theory
 -driven-data-science/
DESCRIPTION;CHARSET=UTF-8:Hybrid Modelling and Theory-Driven Data Science\n
 Data-driven models have gone everywhere: Backed by their successes in comp
 arably recent technological fields such as image processing or speech reco
 gnition and powered by ongoing digitization\, data-driven models have been
  taken up in all disciplines. In some of these disciplines\, a large amoun
 t of domain knowledge is available in the form of (physical) theories – 
 for example\, in manufacturing or pharmaceutical industries\, this domain 
 knowledge may come in the shape of differential equations repr\n\nHybrid M
 odelling and Theory-Driven Data Science\n\n05.08.2020 15:00 &#8211\; 17:00
  | Language: English\n\n\nTarget Group\nResearchers from manufacturing or 
 pharmaceutical industry\nAbstract\nData-driven models have gone everywhere
 : Backed by their successes in comparably recent technological fields such
  as image processing or speech recognition and powered by ongoing digitiza
 tion\, data-driven models have been taken up in all disciplines. In some o
 f these disciplines\, a large amount of domain knowledge is available in t
 he form of (physical) theories – for example\, in manufacturing or pharm
 aceutical industries\, this domain knowledge may come in the shape of diff
 erential equations representing the behavior of materials or the reactions
  within a process describing the system under study.\nRather than suggesti
 ng data-driven models as a substitute for this theoretical knowledge\, the
  present talk will give an insight into how this knowledge can be incorpor
 ated into the data-driven models. The combined – hybrid – model will g
 enerally have a larger consistency with the physical world and\, due to th
 e use of data\, a higher accuracy than its theoretical counterpart. We wil
 l illustrate the various ways to combine theoretical with data-driven mode
 ls at the hand of several success stories achieved at the Know-Center.\nIn
  the second part of the session\, we ask for your input: What is the type 
 of knowledge available in your profession? And for what problems do you cu
 rrently foresee data-driven models as promising approaches? What are the m
 ajor roadblocks that you see ahead? Allocating speaker time to all attende
 es will open the forum for discussing how theory-guided data science can b
 e put to good use in your respective field.\nAfter the event you will know
 :\nThe manifold possibilities of incorporating theoretical knowledge into 
 data-driven models\, e.g.\,\n\n\n\nHow deep learning can solve differentia
 l equations\n\n\n\n\n\n\nHow domain knowledge can help in feature engineer
 ing\n\n\n\n\n\n\nHow a data-driven approach can improve approximate physic
 al models\n\n\n\nFurthermore\, you will learn about\n\n\n\nPrevious succes
 s stories in theory-driven data science and hybrid modelling\n\n\n\n\n\n\n
 The future research direction of Know-Center in this field\n\n\n\n\nSpeake
 r\n\n\n\n\n\nBernhard Geiger\nKnowledge Discovery\n\n\n\n\n
LOCATION;CHARSET=UTF-8:
END:VEVENT
END:VCALENDAR