BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:TEST INSTANCE Understanding large language models for science and
DTSTART:20260514T070000Z
DTEND:20260514T130000Z
DTSTAMP:20260617T185000Z
UID:indico-event-3827@indico.ijs.si
CONTACT:events@slaif.si
DESCRIPTION:Speakers: Marko Robnik-Šikonja\n\nTEST INSTANCE\nCourse provi
 der: University of Ljubljana\, Faculty of Computer and Information Scienc
 e (UL FRI)Instructors: Marko Robnik-Šikonja (UL FRI)\nLearning objectives
 : Get acquainted with large language models (LLMs)\, their architecture an
 d training\, leading to their effective use.\nCourse contents: Large langu
 age models are changing the way we write\, read\, and do intellectual jobs
 . The lecture presents the working of the transformer architecture of neur
 al networks and focuses on the decoder models\, which are used in generati
 ve language models\, such as ChatGPT. Explaining their construction\, pret
 raining\, instruction following\, preference alignment\, and fine-tuning\,
  the lecture gives the necessary background to understand their behaviour.
  Based on this\, it explains prompting strategies\, such as in-context lea
 rning and chain-of-thought reasoning. The contents are based on examples f
 rom business and science.\nLearning outcomes: Knowledge of LLM constructio
 n and recommendations for their use.\n\nhttps://indico.ijs.si/event/3827/
LOCATION:UL FRI
URL:https://indico.ijs.si/event/3827/
END:VEVENT
END:VCALENDAR